phi-2-gpo-renew2-b0.001-extra-i1 [bfloat16] [Adapter] [rev: d9251dd7ee40]: benchmark results

Provider: Microsoft. Access: Open.

Aggregate Rating 1374 ± 35, rank #7057 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K55.42Accuracy (%) (5-shot)67
Open LLM Leaderboard v1 - ARC Challenge61.35Normalized accuracy (%) (25-shot)52.5
Open LLM Leaderboard v1 - MMLU57.97Accuracy (%) (5-shot)42.3
Open LLM Leaderboard v1 - WinoGrande73.64Accuracy (%) (5-shot)32.9
Open LLM Leaderboard v1 - TruthfulQA MC244.74MC2 (%) (0-shot)28.3
Open LLM Leaderboard v1 - HellaSwag74.87Normalized accuracy (%) (10-shot)25.4

Interactive version: theaggregate.ai/model?slug=phi-2-gpo-renew2-b0-001-extra-i1-bfloat16-adapter-rev-d9251dd7ee40 · How It Works · Data refreshed daily, snapshot 2026-11-08.