| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| trail-benchmark | ASRL | Top-1 Accuracy100 | 4 | 4d ago | |
| MedAgentBench | Top-1 Acc100 | 4 | 4d ago | ||
| MCPToolBenchPP | Top-1 Acc100 | 4 | 4d ago | ||
| GTA | ASRL | Top-1 Acc100 | 4 | 4d ago | |
| Agents Failure Attribution | ASRL | Top-1 Accuracy100 | 4 | 4d ago | |
| agent-data protocol | ASRL | Top-1 Acc100 | 4 | 4d ago |