Phi-3 Mini 4K Instruct (Publisher: unsloth): benchmark results
Provider: Microsoft. Access: Open.
Aggregate Rating 1453 ± 33, rank #3653 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 73.92 | Accuracy (%) (5-shot) | 98.9 |
| Open LLM Leaderboard v1 - MMLU | 69.08 | Accuracy (%) (5-shot) | 92.1 |
| Open LLM Leaderboard - GPQA | 32.3 | Score | 77 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 59.88 | MC2 (%) (0-shot) | 74.8 |
| Open LLM Leaderboard - MMLU-Pro | 40.31 | Score | 74.1 |
| Open LLM Leaderboard - BBH | 55 | Score | 73.5 |
| Open LLM Leaderboard - MuSR | 42.84 | Score | 69 |
| Open LLM Leaderboard - IFEval | 54.4 | Score | 65.5 |
| Open LLM Leaderboard - MATH Level 5 | 16.39 | Score | 64.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.97 | Normalized accuracy (%) (25-shot) | 60.6 |
| Open LLM Leaderboard v1 - HellaSwag | 80.61 | Normalized accuracy (%) (10-shot) | 41.6 |
| Open LLM Leaderboard v1 - WinoGrande | 72.69 | Accuracy (%) (5-shot) | 29.8 |
Interactive version: theaggregate.ai/model?slug=phi-3-mini-4k-instruct-publisher-unsloth · How It Works · Data refreshed daily, snapshot 2026-11-08.