Phi-3-mini-4k-instruct-v0.1: benchmark results
Provider: Microsoft.
Aggregate Rating 1435 ± 37, rank #4375 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 72.25 | Accuracy (%) (5-shot) | 97.5 |
| Open LLM Leaderboard v1 - MMLU | 68.96 | Accuracy (%) (5-shot) | 92 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 61.48 | MC2 (%) (0-shot) | 77.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.63 | Normalized accuracy (%) (25-shot) | 59 |
| Open LLM Leaderboard v1 - HellaSwag | 81.07 | Normalized accuracy (%) (10-shot) | 43.5 |
| Open LLM Leaderboard v1 - WinoGrande | 71.03 | Accuracy (%) (5-shot) | 25.8 |
Interactive version: theaggregate.ai/model?slug=phi-3-mini-4k-instruct-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.