Phi-3-Medium-Llamaish: benchmark results
Provider: Microsoft. Access: Open.
Aggregate Rating 1493 ± 40, rank #2463 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 80.36 | Accuracy (%) (5-shot) | 99.7 |
| Open LLM Leaderboard v1 - MMLU | 77.86 | Accuracy (%) (5-shot) | 99 |
| Open LLM Leaderboard v1 - ARC Challenge | 67.41 | Normalized accuracy (%) (25-shot) | 76.7 |
| Open LLM Leaderboard v1 - HellaSwag | 85.6 | Normalized accuracy (%) (10-shot) | 75.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.87 | MC2 (%) (0-shot) | 66.5 |
| Open LLM Leaderboard v1 - WinoGrande | 73.8 | Accuracy (%) (5-shot) | 33.6 |
Interactive version: theaggregate.ai/model?slug=phi-3-medium-llamaish · How It Works · Data refreshed daily, snapshot 2026-11-08.