phi-3-orpo-v9_16: benchmark results
Provider: Microsoft. Access: Open.
Aggregate Rating 1404 ± 36, rank #5871 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 65.26 | Accuracy (%) (5-shot) | 83.5 |
| Open LLM Leaderboard v1 - GSM8K | 62.32 | Accuracy (%) (5-shot) | 75.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.41 | Normalized accuracy (%) (25-shot) | 47.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.76 | MC2 (%) (0-shot) | 45.9 |
| Open LLM Leaderboard v1 - HellaSwag | 78.37 | Normalized accuracy (%) (10-shot) | 33.7 |
| Open LLM Leaderboard v1 - WinoGrande | 70.24 | Accuracy (%) (5-shot) | 24.6 |
Interactive version: theaggregate.ai/model?slug=phi-3-orpo-v9-16 · How It Works · Data refreshed daily, snapshot 2026-11-08.