Phi-2-DPO: benchmark results
Provider: Microsoft. Access: Open.
Aggregate Rating 1372 ± 34, rank #7122 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 55.88 | Accuracy (%) (5-shot) | 67.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.75 | Normalized accuracy (%) (25-shot) | 49.3 |
| Open LLM Leaderboard v1 - MMLU | 57.75 | Accuracy (%) (5-shot) | 41.8 |
| Open LLM Leaderboard v1 - WinoGrande | 73.64 | Accuracy (%) (5-shot) | 32.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.46 | MC2 (%) (0-shot) | 27.2 |
| Open LLM Leaderboard v1 - HellaSwag | 75.03 | Normalized accuracy (%) (10-shot) | 25.7 |
Interactive version: theaggregate.ai/model?slug=phi-2-dpo · How It Works · Data refreshed daily, snapshot 2026-11-08.