Phi-3-mini-128k-instruct-HumanChoice-4.6k-DPO: benchmark results
Provider: Microsoft.
Aggregate Rating 1430 ± 36, rank #4647 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 68.62 | Accuracy (%) (5-shot) | 91.7 |
| Open LLM Leaderboard v1 - GSM8K | 69.75 | Accuracy (%) (5-shot) | 90.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 54.51 | MC2 (%) (0-shot) | 62.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.97 | Normalized accuracy (%) (25-shot) | 60.6 |
| Open LLM Leaderboard v1 - HellaSwag | 80.09 | Normalized accuracy (%) (10-shot) | 40 |
| Open LLM Leaderboard v1 - WinoGrande | 73.01 | Accuracy (%) (5-shot) | 30.7 |
Interactive version: theaggregate.ai/model?slug=phi-3-mini-128k-instruct-humanchoice-4-6k-dpo · How It Works · Data refreshed daily, snapshot 2026-11-08.