phi-2-ko-v0.1: benchmark results
Provider: Microsoft. Access: Open.
Aggregate Rating 1134 ± 35, rank #10228 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 43.64 | MC2 (%) (0-shot) | 24.3 |
| Open LLM Leaderboard v1 - GSM8K | 1.29 | Accuracy (%) (5-shot) | 16.3 |
| Open LLM Leaderboard v1 - MMLU | 27.34 | Accuracy (%) (5-shot) | 15.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 30.72 | Normalized accuracy (%) (25-shot) | 9.7 |
| Open LLM Leaderboard v1 - HellaSwag | 37.26 | Normalized accuracy (%) (10-shot) | 7.4 |
| Open LLM Leaderboard v1 - WinoGrande | 52.72 | Accuracy (%) (5-shot) | 7 |
Interactive version: theaggregate.ai/model?slug=phi-2-ko-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.