EleutherAI/lm-evaluation-harness
A framework for few-shot evaluation of language models.
14.3k
Stars
3.7k
Forks
67.4
Radar Score
Rising
Momentum
Scoring Breakdown
Impact93.0
Velocity49.6
Health51.4
Growth Metrics
7-Day Stars
+81
30-Day Stars
+240
Acceleration
1.40x
Language
Python
Why it ranks
Steady growth — consistently collecting stars and contributors.
Top 87% globallyLast push 33d ago+81 stars / 7d+240 stars / 30d