EleutherAI

eleutherai/lm-evaluation-harness

steady

A framework for few-shot evaluation of language models.

Python View on GitHub

Stars

14,067

Forks

3,598

Open issues

604

24h

+9

+0.1%

7d

+65

+0.5%

Refresh

2h

Star history (7 days)

Last checked

27m ago

Last pushed

14 Sep 2026

Next check

just now