-
Notifications
You must be signed in to change notification settings - Fork 2.9k
Pull requests: openai/evals
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
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…
Route modern OpenAI models through chat completions
#1651
opened Apr 23, 2026 by
kayametehan
Loading…
Update Python version to 3.12 and refresh PR template
#1648
opened Apr 23, 2026 by
kayametehan
Loading…
Add Turkish language evals: logical reasoning and grammar
#1647
opened Apr 23, 2026 by
kayametehan
Loading…
eval: add RAIL Score responsible AI evaluation across 8 dimensions
#1640
opened Apr 2, 2026 by
SumitVermakgp
Loading…
12 tasks done
fix: replace 11 bare except clauses with except Exception
#1626
opened Feb 25, 2026 by
haosenwang1018
Loading…
Add finance-agent routing eval dataset and builder guidance
#1625
opened Feb 24, 2026 by
maxpetrusenko
Loading…
Add Logic Stress Stress-test Suite (v2, v3)
#1622
opened Feb 16, 2026 by
14H034160212
Contributor
Loading…
Add reasoning consistency eval under constrained intermediate steps
#1615
opened Feb 5, 2026 by
getappai
Loading…
Refactor JSONL file loading logic in data.py
#1612
opened Feb 3, 2026 by
Pritiks23
Loading…
13 tasks done
Add tnengoy_citations.dev.v0 (model-graded factuality eval)
#1603
opened Oct 12, 2025 by
TheodorNEngoy
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-04-10.