Phi-5B-Test: benchmark results
Provider: Microsoft.
Aggregate Rating 1327 ± 34, rank #8209 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 54.31 | Accuracy (%) (5-shot) | 33.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 54.61 | Normalized accuracy (%) (25-shot) | 31.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 45.66 | MC2 (%) (0-shot) | 31.7 |
| Open LLM Leaderboard v1 - GSM8K | 10.08 | Accuracy (%) (5-shot) | 31 |
| Open LLM Leaderboard v1 - WinoGrande | 71.98 | Accuracy (%) (5-shot) | 27.8 |
| Open LLM Leaderboard v1 - HellaSwag | 67.6 | Normalized accuracy (%) (10-shot) | 18.6 |
Interactive version: theaggregate.ai/model?slug=phi-5b-test · How It Works · Data refreshed daily, snapshot 2026-11-08.