microsoft-phi-2-sft [bfloat16] [Adapter] [rev: 397f86da5667]: benchmark results

Provider: cloudyu. Access: Open.

Aggregate Rating 1372 ± 34, rank #7095 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K51.18Accuracy (%) (5-shot)63.4
Open LLM Leaderboard v1 - ARC Challenge61.43Normalized accuracy (%) (25-shot)52.8
Open LLM Leaderboard v1 - MMLU57.57Accuracy (%) (5-shot)41.4
Open LLM Leaderboard v1 - WinoGrande74.82Accuracy (%) (5-shot)38.9
Open LLM Leaderboard v1 - TruthfulQA MC244.28MC2 (%) (0-shot)26.5
Open LLM Leaderboard v1 - HellaSwag74.36Normalized accuracy (%) (10-shot)24.6

Interactive version: theaggregate.ai/model?slug=microsoft-phi-2-sft-bfloat16-adapter-rev-397f86da5667 · How It Works · Data refreshed daily, snapshot 2026-11-08.