AE
alpaca_eval
Evaluation·infrastructure·open·#672 of 944·+22·Surging
65.2
Low
High confidence
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Pillar Breakdown
Adoption
35%
65.9
Maintenance
30%
64.9
Friction
20%
99.8
Ecosystem
15%
39.3
Momentum
1.00Surging
7d change +0.87
High confidenceIn Evaluation
Ranked #33 of 57