zephyr-7B-dpo-full-beta-0.2 [float16] [rev: 727b63fc1ca6]: benchmark results

Provider: HuggingFace. Access: Open.

Aggregate Rating 1396 ± 33, rank #6288 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC254.78MC2 (%) (0-shot)63.5
Open LLM Leaderboard v1 - HellaSwag83.98Normalized accuracy (%) (10-shot)62.9
Open LLM Leaderboard v1 - ARC Challenge61.86Normalized accuracy (%) (25-shot)54.8
Open LLM Leaderboard v1 - MMLU61.85Accuracy (%) (5-shot)53.1
Open LLM Leaderboard v1 - WinoGrande76.95Accuracy (%) (5-shot)52
Open LLM Leaderboard v1 - GSM8K28.73Accuracy (%) (5-shot)46.2

Interactive version: theaggregate.ai/model?slug=zephyr-7b-dpo-full-beta-0-2-float16-rev-727b63fc1ca6 · How It Works · Data refreshed daily, snapshot 2026-11-08.