HE
human-eval
Evaluation·infrastructure·open·#771 of 884·+91·Stable
59.5
Low
High confidence
Code for the paper "Evaluating Large Language Models Trained on Code"
Pillar Breakdown
Adoption
35%
46.8
Maintenance
30%
64.3
Friction
20%
97.4
Ecosystem
15%
43.9
Momentum
0.31Stable
7d change -0.26
High confidenceIn Evaluation
Ranked #43 of 57