phi-1.5_chat: benchmark results
Provider: Microsoft.
Aggregate Rating 1272 ± 36, rank #9040 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 21.46 | Accuracy (%) (5-shot) | 41.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 43.94 | MC2 (%) (0-shot) | 25.2 |
| Open LLM Leaderboard v1 - WinoGrande | 70.72 | Accuracy (%) (5-shot) | 25.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 50.51 | Normalized accuracy (%) (25-shot) | 24.8 |
| Open LLM Leaderboard v1 - MMLU | 40.5 | Accuracy (%) (5-shot) | 21.2 |
| Open LLM Leaderboard v1 - HellaSwag | 61.03 | Normalized accuracy (%) (10-shot) | 14.9 |
Interactive version: theaggregate.ai/model?slug=phi-1-5-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.