| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TRAIL | SARL | Top-1 Accuracy98.15 | 4 | 4d ago | |
| MedAgentBench | Top-1 Accuracy99 | 4 | 4d ago | ||
| MCPToolBench++ | SARL | Top-1 Acc77.57 | 4 | 4d ago | |
| GTA | Top-1 Acc100 | 4 | 4d ago | ||
| Agents Failure Attribution | Top-1 Accuracy95.3 | 4 | 4d ago | ||
| Agent-data-protocol | SARL | Top-1 Accuracy79.85 | 4 | 4d ago |