phi-2 [float16] [rev: d3186761bf5c]: benchmark results
Microsoft's Phi-2 base transformer, trained on synthetic NLP text and filtered websites without RLHF fine-tuning. This row preserves its separately evaluated revision, precision, shot count or runtime configuration. Provider: Microsoft. Access: Open.
Aggregate Rating 1375 ± 34, rank #7030 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 54.81 | Accuracy (%) (5-shot) | 66.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.09 | Normalized accuracy (%) (25-shot) | 51.2 |
| Open LLM Leaderboard v1 - MMLU | 58.11 | Accuracy (%) (5-shot) | 42.6 |
| Open LLM Leaderboard v1 - WinoGrande | 74.35 | Accuracy (%) (5-shot) | 36.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.47 | MC2 (%) (0-shot) | 27.3 |
| Open LLM Leaderboard v1 - HellaSwag | 75.11 | Normalized accuracy (%) (10-shot) | 25.9 |
Interactive version: theaggregate.ai/model?slug=phi-2-float16-rev-d3186761bf5c · How It Works · Data refreshed daily, snapshot 2026-11-08.