phi-2-dpo [Adapter]: benchmark results

Provider: Microsoft. Access: Open.

Aggregate Rating 1380 ± 35, rank #6840 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K56.71Accuracy (%) (5-shot)68.5
Open LLM Leaderboard v1 - ARC Challenge63.05Normalized accuracy (%) (25-shot)61
Open LLM Leaderboard v1 - MMLU58.46Accuracy (%) (5-shot)43.4
Open LLM Leaderboard v1 - WinoGrande74.03Accuracy (%) (5-shot)34.6
Open LLM Leaderboard v1 - TruthfulQA MC245.35MC2 (%) (0-shot)30.5
Open LLM Leaderboard v1 - HellaSwag76.36Normalized accuracy (%) (10-shot)28.5

Interactive version: theaggregate.ai/model?slug=phi-2-dpo-adapter · How It Works · Data refreshed daily, snapshot 2026-11-08.