METR Task Standard
EvalsFramework / harness (not an eval — tooling/reference entry)
Standard format for defining agent tasks.
- Category
- Eval frameworks & harnesses
- Insurance exposure
- Unmapped
- Publisher
- METR
- Publisher type
- Nonprofit / research org
- License
- MIT
- Status
- Active (<90d) / deprecated
- Last commit
- 2026-10-07
- Stars
- 198
- Notes
- METR no longer maintains; moved to Inspect.
Wanich Risk Lab, 2026.