zephyr-7B-dpo-full: benchmark results

Provider: HuggingFace. Access: Open.

Aggregate Rating 1383 ± 34, rank #6759 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag84.45Normalized accuracy (%) (10-shot)66.2
Open LLM Leaderboard v1 - ARC Challenge62.88Normalized accuracy (%) (25-shot)60.2
Open LLM Leaderboard v1 - WinoGrande76.64Accuracy (%) (5-shot)49.6
Open LLM Leaderboard v1 - MMLU59.56Accuracy (%) (5-shot)45.4
Open LLM Leaderboard v1 - GSM8K18.57Accuracy (%) (5-shot)39.9
Open LLM Leaderboard v1 - TruthfulQA MC247.41MC2 (%) (0-shot)37.6

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