phi-3-22B: benchmark results
Provider: Microsoft.
Aggregate Rating 1480 ± 37, rank #2661 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 74.45 | Accuracy (%) (5-shot) | 99.1 |
| Open LLM Leaderboard v1 - MMLU | 76.15 | Accuracy (%) (5-shot) | 97.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 67.58 | Normalized accuracy (%) (25-shot) | 77.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 53.74 | MC2 (%) (0-shot) | 60.5 |
| Open LLM Leaderboard v1 - WinoGrande | 77.74 | Accuracy (%) (5-shot) | 58.2 |
| Open LLM Leaderboard v1 - HellaSwag | 83.03 | Normalized accuracy (%) (10-shot) | 55.5 |
Interactive version: theaggregate.ai/model?slug=phi-3-22b · How It Works · Data refreshed daily, snapshot 2026-11-08.