phi-2-gpo-renew2-b0.001-vllm-i1 [Adapter]: benchmark results

Provider: Microsoft. Access: Open.

Aggregate Rating 1373 ± 34, rank #7066 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 Challenge61.26Normalized accuracy (%) (25-shot)52
Open LLM Leaderboard v1 - MMLU57.86Accuracy (%) (5-shot)42
Open LLM Leaderboard v1 - WinoGrande73.95Accuracy (%) (5-shot)34.2
Open LLM Leaderboard v1 - TruthfulQA MC244.33MC2 (%) (0-shot)26.7
Open LLM Leaderboard v1 - HellaSwag75.08Normalized accuracy (%) (10-shot)25.8

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