OpenHands / OpenHands/benchmarks

Port ProgramBench benchmark to Harbor

Open
#723 0 comments 0 reactions 0 assignees View on GitHub

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-eval workflow.

Acceptance criteria

  • ProgramBench tasks can be run through Harbor.
  • Evaluation output matches upstream ProgramBench expectations.
  • Parity results and resource caveats are documented.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.