OpenHands / OpenHands/benchmarks
Port ProgramBench benchmark to Harbor
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 124
- Forks
- 90
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 1
Description
Context
benchmarks/programbench currently contains substantial benchmark-specific inference and evaluation logic for cleanroom task images and ProgramBench submission/evaluation behavior. A Harbor adapter is needed before this benchmark can be removed from the bespoke OpenHands path.
Proposed scope
- Create a Harbor adapter/dataset for ProgramBench tasks.
- Preserve cleanroom task image usage, workspace submission format, and upstream evaluation semantics.
- Support resource settings appropriate for ProgramBench long rebuild tasks.
- Run parity against the current
programbench-infer/programbench-evalworkflow.
Acceptance criteria
- ProgramBench tasks can be run through Harbor.
- Evaluation output matches upstream ProgramBench expectations.
- Parity results and resource caveats are documented.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading benchmarks/programbench and tracing the existing programbench-infer and programbench-eval workflow. Identify how cleanroom task images, workspace submissions, evaluation semantics, and long rebuild resource settings are handled. Done means ProgramBench runs through Harbor, produces upstream-compatible evaluation output, and documents parity results and resource caveats.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- devtools, testing-qa
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100