ToolRL
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Function calling | ToolRL 80-prompt (held-out) | Best@394 | 8 | |
| Tool Use | ToolRL prompts (hold-out) | Pre-Reconstruction Tool Correctness19 | 2 |
Showing 2 of 2 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Function calling | ToolRL 80-prompt (held-out) | Best@394 | 8 | |
| Tool Use | ToolRL prompts (hold-out) | Pre-Reconstruction Tool Correctness19 | 2 |