phi-2-orange-v2: benchmark results
Provider: Microsoft. Released 2024-03-04. Access: Open.
Aggregate Rating 1370 ± 27, rank #7177 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 57.62 | Accuracy (%) (5-shot) | 69.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 54.84 | MC2 (%) (0-shot) | 63.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.86 | Normalized accuracy (%) (25-shot) | 54.8 |
| Open LLM Leaderboard v1 - WinoGrande | 75.69 | Accuracy (%) (5-shot) | 43.5 |
| Open LLM Leaderboard - BBH | 47.7 | Score | 40.7 |
| Open LLM Leaderboard v1 - MMLU | 55.72 | Accuracy (%) (5-shot) | 37.1 |
| Open LLM Leaderboard - IFEval | 36.7 | Score | 35.2 |
| Open LLM Leaderboard v1 - HellaSwag | 76.32 | Normalized accuracy (%) (10-shot) | 28.4 |
| Open LLM Leaderboard - MMLU-Pro | 25.32 | Score | 25.9 |
| YALL Nous Leaderboard | 47.89 | Average | 25.9 |
| Open LLM Leaderboard - MATH Level 5 | 4.08 | Score | 23.4 |
| Open LLM Leaderboard - MuSR | 36.3 | Score | 19.5 |
Interactive version: theaggregate.ai/model?slug=phi-2-orange-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.