Skip to content

Conversation

@jim-bo
Copy link
Contributor

@jim-bo jim-bo commented Dec 12, 2025

Hey I made some changes to clean up how LEADERBOARD.md is created and I setup the two null agents to use distinct "null prompts".

@jim-bo jim-bo requested review from gisetia and inodb December 12, 2025 15:21
Copy link
Member

@inodb inodb left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks sensible to me! Thank you!

Copy link
Member

@gisetia gisetia left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

looks good

@gisetia
Copy link
Member

gisetia commented Dec 15, 2025

I noticed there is an extra comma here:

f"# Average {col}: {averages[col]:.2f},,,,,,,,," for col in numeric_cols]

Has 9 commas, but should be 8. So the evaluation csv is not nicely rendered in github

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants