Loading ToolBench
GitHub Action for running SWE-bench Pro benchmarks using mcpbr (MCP-based runner). Supports preflight validation and evaluation modes with Docker-based task execution.
Scoring was not performed
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 0 | 2026-07-28+ | v2 |