Skip to content

Pull requests: openai/evals

New pull request New
Clear current search query, filters, and sorts
49 Open 1,244 Closed
49 Open 1,244 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Chess eval: Changed typo 'beset' to 'best' in all 101 examples.
#1374 opened Oct 3, 2023 by Zirunis • Approved
1 ❤️ 1
Add gpt4facts Eval
#1363 opened Sep 25, 2023 by mmtmn • Review required
13 tasks done
3
Add few-shot-abuse eval
#478 opened Mar 28, 2023 by githubman2718 • Review required
12 tasks done
Emergency department classification eval
#587 opened Apr 5, 2023 by abhinayvyas • Review required
11 tasks done
2
Race & Gender Bias
#630 opened Apr 10, 2023 by nickls • Review required
11 of 12 tasks
2
Intracerebral Haemorrhage Prediction in Patients with Complex Chronic…
#688 opened Apr 15, 2023 by odeak • Review required
11 of 12 tasks
commonsense morality
#750 opened Apr 22, 2023 by lucid-max • Review required
12 tasks done
Eval: Advanced emotion analysis for complex scenarios based on a Ph.D. dissertation
#836 opened Apr 27, 2023 by tuanlemau • Review required
11 of 12 tasks
2
Now I have the change in place, it seems wrong.
#1209 opened Jun 21, 2023 by CholoTook • Review required
[Resolves Issue #1228] Improve ModelGraded Evals Formatting for Increased GPT Compliance
#1258 opened Jun 28, 2023 by douglasmonsky • Review required
1
4
add eval against machiavellianistic attitudes
#1270 opened Jul 1, 2023 by Huge • Review required
2
Nits
#1308 opened Jul 7, 2023 by mrzu • Draft
5 of 6 tasks
MMLU eval
#1324 opened Jul 29, 2023 by Livegan • Review required
13 tasks
[evals] Jailbreaks for refusal of harmful content
#291 opened Mar 17, 2023 by devxpy • Review required
10 of 12 tasks
Add a new eval : chinese_literary_grace
#1375 opened Oct 7, 2023 by Conghui-Niu • Review required
12 of 13 tasks
3
Deepcopy in recorder
#1376 opened Oct 12, 2023 by johny-b • Review required
1
Valid Hanabi clues eval & update Includes to optionally take Exclusions
#1385 opened Oct 17, 2023 by sjadler2004 • Review required
13 tasks done
5
Add Eval: name well known security weaknesses
#1392 opened Oct 28, 2023 by ourmony Loading…
1 task
1
Choose completion function for evaluation of modelgraded evals
#1418 opened Nov 17, 2023 by LoryPack Loading…
6 tasks done
Adding Indian Women Menstrual Health Chatbot Eval
#1430 opened Dec 11, 2023 by cranberrydeveloper Loading…
13 tasks done
8
Extending to Azure OpenAI implementation
#1470 opened Feb 23, 2024 by pkt1583 Loading…
7
Add **kwargs to OpenAIChatCompletionFn
#1494 opened Mar 15, 2024 by ezraporter Loading…
1
[Evals] Add eval for Dhivehi diacritical marks
#1495 opened Mar 16, 2024 by aanaseer Loading…
11 of 12 tasks
1
Fix AttributeError: Update OpenAI error imports (Closes #1564)
#1577 opened Jan 27, 2025 by SaiKrishna-KK Loading…
6 of 13 tasks
1
1
Add Eval: Interpreting balance sheet absolute changes
#1336 opened Aug 16, 2023 by TensorTemplar Loading…
12 of 13 tasks
3
ProTip! Follow long discussions with comments:>50.