Phi-3-mini-4k-instruct-v0.3: benchmark results
Provider: Microsoft.
Aggregate Rating 1439 ± 36, rank #4231 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 74.53 | Accuracy (%) (5-shot) | 99.1 |
| Open LLM Leaderboard v1 - MMLU | 69.24 | Accuracy (%) (5-shot) | 92.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 60.66 | MC2 (%) (0-shot) | 76.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.48 | Normalized accuracy (%) (25-shot) | 62.9 |
| Open LLM Leaderboard v1 - HellaSwag | 80.86 | Normalized accuracy (%) (10-shot) | 42.6 |
| Open LLM Leaderboard v1 - WinoGrande | 72.77 | Accuracy (%) (5-shot) | 30.1 |
Interactive version: theaggregate.ai/model?slug=phi-3-mini-4k-instruct-v0-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.