Skip to content

Pull requests: OpenHands/benchmarks

New pull request New
18 Open 149 Closed
18 Open 149 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Make multi-swe-bench an optional dependency to fix corrupted wheel
#290 opened Jan 9, 2026 by greynewell Loading…
Add swebenchmultimodal support to CI workflows
#289 opened Jan 9, 2026 by juanmichelini Loading…
Fix cost report generation for JSONL files with null entries
#288 opened Jan 9, 2026 by juanmichelini Loading…
4
Persist conversation events to runtime
#285 opened Jan 8, 2026 by simonrosenberg Loading…
2
build(deps): bump the version-all group across 1 directory with 15 updates dependencies Pull requests that update a dependency file python:uv Pull requests that update python:uv code
#278 opened Jan 7, 2026 by dependabot bot Loading…
Sr/run 500 image job
#269 opened Jan 7, 2026 by simonrosenberg • Draft
1
refactor(gaia): use evaluation framework for max_retries parameter
#268 opened Jan 6, 2026 by juanmichelini Loading…
1
Require main and critic outputs
#252 opened Jan 6, 2026 by simonrosenberg Loading…
1
Add configurable conversation timeout to all benchmarks
#250 opened Jan 5, 2026 by simonrosenberg • Draft
[DRAFT] latest main build-swebench Build 500 SWE-Bench Verified Image based on SDK version on this PR.
#248 opened Jan 5, 2026 by xingyaoww • Draft
SWT-bench: cache preload, latency instrumentation, pydantic-core bump
#245 opened Jan 5, 2026 by simonrosenberg • Draft
1
1
Add output_jsonl_gcs input forwarding
#237 opened Jan 3, 2026 by simonrosenberg Loading…
1
Add OpenAgentSafety to eval CI
#221 opened Dec 29, 2025 by simonrosenberg Loading…
1
Add Multi-SWE-bench image build support
#219 opened Dec 29, 2025 by simonrosenberg Loading…
1
Add add_resolve_rate_to_predictions function to output_utils
#199 opened Dec 23, 2025 by juanmichelini • Draft
1
1
Agentic code search
#141 opened Dec 8, 2025 by adityasoni9998 Loading…
5
Fix Browser action deserialization by using OpenHandsModel
#136 opened Dec 6, 2025 by simonrosenberg • Draft
2
API-based Critic implementation build-swebench-200 Build 200 SWE-Bench Verified Image based on SDK version on this PR.
#117 opened Nov 26, 2025 by xingyaoww • Draft
2
ProTip! Updated in the last three days: updated:>2026-01-06.