specific method · not yet filed
sandboxed agentic benchmarking on a Harbor fork with step limit
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
All Laguna S 2.1 agentic benchmarking was completed using our internal fork of the Laude Institute's Harbor Framework with our agent harness, a maximum of 500 steps and sandboxed execution via our internal sandbox service.
usedevaluation onlyPoolside