AgentDish directory
Terminal-Bench
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
|
#17
↓ -2
BoundaryBench
BoundaryBench is an open-source benchmark for coding agents running under hardened sandbox policies. It compares harnesses like Claude Code, Codex, Terminus 2, and Grok on Terminal-Bench tasks and includes quickstart, policy controls, and result export tools. |
Developer Tools / Code Assistant | 90 | ↓ -2 | just now | Details |