Loading ToolBench
Multi-agent system over MCP — DAG planning, ReAct execution, auto-replanning — benchmarked against the official MCP-Bench single-agent runner.
Scoring was not performed
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 0 | 2026-07-28+ | v2 |