Phi-3-mini-4k-instruct-v0.2: benchmark results
Provider: Microsoft.
Aggregate Rating 1436 ± 37, rank #4346 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 73.62 | Accuracy (%) (5-shot) | 98.8 |
| Open LLM Leaderboard v1 - MMLU | 69.1 | Accuracy (%) (5-shot) | 92.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 59.97 | MC2 (%) (0-shot) | 75 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.8 | Normalized accuracy (%) (25-shot) | 59.8 |
| Open LLM Leaderboard v1 - HellaSwag | 80.76 | Normalized accuracy (%) (10-shot) | 42.3 |
| Open LLM Leaderboard v1 - WinoGrande | 72.45 | Accuracy (%) (5-shot) | 29.1 |
Interactive version: theaggregate.ai/model?slug=phi-3-mini-4k-instruct-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.