specific method · filed under software implementation
OpenHands
An agent harness used in model training contexts and in a SWE-Bench Pro evaluation.
- sources
- 2
- models
- 2
- labs adopt it
- 2
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
the model is trained under at least two of the following harnesses: • Stirrup • OpenHands • OpenCode • Terminus • Droid
usedsoftware implementationin Nemotron 3 UltraNVIDIA
We run the SWE-Bench Pro suite with OpenHands
usedevaluation onlyin GLM-5.2Z.ai
Filed alongside
Other methods under software implementation :: agent product.