Skip to content

Release v1.0.0 - #1

Merged
skrsteski merged 1 commit into
mainfrom
release/v1.0.0
Sep 27, 2026
Merged

skrsteski merged 1 commit into
mainfrom
release/v1.0.0

Conversation

@github-actions

Copy link
Copy Markdown

MESSIER v1.0.0

We release the first public version of MESSIER.

  • Corpus. 902,338 records from 31 benchmarks, 725 agents, 11,999 tasks, and 72,000 verifiers.
  • Data. The release contains task definitions, results, verifier definitions, and 118,089 available trajectories.
  • Code. The repository includes dataset builders, loaders, validation checks, IRT models, paper analyses, and the project page.

Dataset candidate

Review the Hugging Face candidate

@skrsteski skrsteski self-assigned this Sep 27, 2026
@skrsteski
skrsteski merged commit 903ed44 into main Sep 27, 2026
@skrsteski
skrsteski deleted the release/v1.0.0 branch September 27, 2026 07:18
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.

1 participant