MCP-Bench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Tool-augmented agent execution | MCP-Bench | Task Fulfillment53.5 | 32 | |
| Agentic Tool Use | MCP-Bench 3-server 1.0 | Overall Score3.95 | 20 | |
| Agentic Tool Use | MCP-Bench Single 1.0 | Overall Score3.54 | 20 | |
| Agent Performance Evaluation | MCP-Bench | Task Fulfillment46.8 | 7 | |
| End-to-End Question Answering | MCP-Bench | Accuracy (Human)87.5 | 4 |
Showing 5 of 5 rows