| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Tool Calling | ToolACE 1000 tools | TSA78.72 | 9 | |
| Tool Calling | ToolACE 500 tools | TSA82.28 | 9 | |
| Intent Alignment | ToolACE | Aintent (GPT-5.0)85.71 | 6 | |
| Intent Inversion Attack | ToolACE | S_text81.39 | 6 | |
| Tool Calling | ToolACE multi-turn (test) | Accuracy61.64 | 2 | |
| Tool Identification | ToolACE multi-turn (test) | Accuracy75.34 | 2 | |
| Function Calling | ToolAce (test) | Accuracy (Single)84.4 | 2 |