Skip to content

Pull requests: openai/evals

New pull request New
90 Open 1,263 Closed
90 Open 1,263 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

docs: add community health files and README updates
#1691 opened Jul 9, 2026 by Mukller Loading…
Add SelfCorrectionEval: self-correction benchmark for reasoning models
#1686 opened Jul 1, 2026 by jxsh341 Loading…
Clarify pip install is for running pre-built evals
#1684 opened Jun 29, 2026 by AgenticSpark Loading…
1
Fix unbalanced ideal labels in balance_chemical_equation samples
#1683 opened Jun 28, 2026 by AgenticSpark Loading…
1
Add healthcare_ai_governance eval (governance decisions on PHI, permissions, clinical safety)
#1682 opened Jun 27, 2026 by haverAI Loading…
4 tasks done
1
Handle structured token usage details
#1680 opened Jun 19, 2026 by AgenticSpark Loading…
1
Expand reasoning consistency evaluation dataset and fix CI issues
#1679 opened Jun 15, 2026 by getappai Loading…
13 tasks
Avoid mutating dicts in jsondumps
#1678 opened Jun 10, 2026 by RaghunandanKumar Loading…
Add BGPT REFUTE benchmark
#1674 opened Jun 5, 2026 by connerlambden Loading…
1
Fix compute_matthew_corr mutating its input confusion matrix
#1672 opened May 28, 2026 by Kymi808 Loading…
fix: sanitize user-supplied command before logging to prevent log injection
#1671 opened May 25, 2026 by rajkumar-prog Loading…
1
Fix EVALS_SHOW_EVAL_PROGRESS env var parsing
#1670 opened May 21, 2026 by LeSingh1 Loading…
fix: prevent stack trace exposure in flask-playwright API responses
#1669 opened May 21, 2026 by rajkumar-prog Loading…
1
fix: guard against empty/filtered LLM responses in make_me_say utils
#1666 opened May 18, 2026 by qizwiz Loading…
fix: omit non-numeric usage fields from token usage report
#1664 opened May 16, 2026 by rajkumar-prog Loading…
1
Refresh contribution documentation references
#1662 opened May 15, 2026 by MukundaKatta Loading…
feat: add MiniMax provider with M3 as default model
#1661 opened May 13, 2026 by octo-patch Loading…
chore: remove obsolete GPT-4 PR guidance
#1659 opened May 11, 2026 by extrasmall0 Loading…
1
1
Add agent pre-action control eval
#1658 opened May 10, 2026 by mindbomber Loading…
13 tasks done
2
Add atr_prompt_injection eval (modelgraded safety, 16 multilingual samples)
#1657 opened May 10, 2026 by eeee2345 Loading…
13 tasks done
Add agent-tool-abstention eval (13 samples, Match template)
#1656 opened May 8, 2026 by MukundaKatta Loading…
5 tasks done
Add agent-tool-routing eval (12 samples, Match template)
#1655 opened May 8, 2026 by MukundaKatta Loading…
5 tasks done
eval: add Oracle ERP Cloud workflow and terminology eval
#1654 opened May 4, 2026 by karthikchundi-commits Loading…
Fix OpenAI completion args routing
#1653 opened Apr 23, 2026 by kayametehan Loading…
1
1
Add explain mode to HumanCliSolver
#1652 opened Apr 23, 2026 by kayametehan Loading…
1
4
ProTip! Mix and match filters to narrow down what you’re looking for.