phi-2-sft: benchmark results
Provider: Microsoft.
Aggregate Rating 1260 ± 51, rank #9165 of 10916 rated models, from 3 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AlpacaEval 1.0 | 68.53 | Win Rate (%) | 23.8 |
| AlpacaEval | 44.74 | Length-Controlled Win Rate (%) | 15.8 |
| AlpacaEval 2.0 | 5.85 | LC Win Rate (%) | 8.1 |
Interactive version: theaggregate.ai/model?slug=phi-2-sft · How It Works · Data refreshed daily, snapshot 2026-11-08.