Seal-Tools
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Tool Calling | Seal-Tools Single-Tool | Name Match Score98.14 | 30 | |
| Tool Calling | Seal-Tools Single-Tool v1 (test) | F1 Name98.14 | 12 | |
| Function Calling | Seal-Tools | F1 Score94.94 | 11 | |
| Multi-tool calling | SEAL-Tools | TSA86.5 | 9 | |
| Tool Retrieval | Seal-Tools (test) | Recall@588.4 | 5 | |
| Tool Selection | Seal-Tools (test) | Top-1 Acc99.9 | 2 | |
| Agent-team recommendation | Seal-Tools (test) | Retrieval Success (Top-10)99.6 | 2 |
Showing 7 of 7 rows