Open CoT Leaderboard

👋 We're running the evaluations and hosting results that underpin the Open CoT Leaderboard.

For more information about the evaluation pipeline, have a look at our Github repo.

To get started with exploring the evaluation results on your own, check out this notebook.

If you want to run and contribute evaluations to the Open CoT Leaderboard, please apply for membership in this organization. We'll get back to you asap.

We're grateful to

• AI2 | KIT's DebateLab | Logikon AI | Helmholtz Association Initiative and Networking Fund on the HAICORE@KIT partition | HoreKa supercomputer funded by the Ministry of Science, Research and the Arts Baden-Württemberg and by the Federal Ministry of Education and Research

for supporting this project.