10 Pull requests merged by 2 people

• remove old grading function implementations

  #747 merged Dec 18, 2024

• More details in consistency check outputs

  #765 merged Dec 18, 2024

• Remove 0.5 code

  #743 merged Dec 18, 2024

• Modelbench SUT cleanup + testing infra improvements

  #754 merged Dec 18, 2024

• Remove SUT wrapper

  #758 merged Dec 18, 2024

• Fix secrets bug in SafeTest

  #763 merged Dec 18, 2024

• fix missing scheme in URL

  #757 merged Dec 17, 2024

• Add partial support for French prompt sets

  #744 merged Dec 17, 2024

• reference scores for an initial set of fr_fr practice prompts

  #751 merged Dec 13, 2024

• fix how AI is capitalized

  #749 merged Dec 13, 2024

3 Pull requests opened by 2 people

• Bump pytest from 8.3.3 to 8.3.4 in the dev-deps group

  #755 opened Dec 16, 2024

• Bump the prod-deps group with 4 updates

  #756 opened Dec 16, 2024

• Get rid of unneeded secret injection in test

  #766 opened Dec 18, 2024

11 Issues opened by 2 people

• Replace Locale object with just strings

  #764 opened Dec 18, 2024

• User bug: missing secrets for private modellab files when running public benchmark

  #762 opened Dec 18, 2024

• Fix smoke test

  #761 opened Dec 17, 2024

• Make it obvious if annotator is not deployed successfully

  #760 opened Dec 17, 2024

• Rerun 3 SUTs with French prompts

  #759 opened Dec 17, 2024

• Get rid of SUT wrapper

  #753 opened Dec 16, 2024

• Generate shareable report after a benchmark is run

  #752 opened Dec 13, 2024

• Run calibration for French prompts

  #750 opened Dec 13, 2024

• Fix capitalization of "AI"

  #748 opened Dec 13, 2024

• Publish results for moderated Mistral SUTs

  #746 opened Dec 12, 2024

• Replace static site generator with something simpler

  #745 opened Dec 12, 2024

3 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Remove 0.5 code

  #741 commented on Dec 13, 2024 • 0 new comments

• Update disclaimer text referencing version 0.5

  #733 commented on Dec 13, 2024 • 0 new comments

• Run 3 SUTs with French prompts

  #739 commented on Dec 14, 2024 • 0 new comments