zephyr-dpo-v2: benchmark results

Provider: HuggingFace. Access: Open.

Aggregate Rating 1373 ± 33, rank #7067 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC256.16MC2 (%) (0-shot)67.2
Open LLM Leaderboard v1 - HellaSwag82.72Normalized accuracy (%) (10-shot)53.3
Open LLM Leaderboard v1 - GSM8K30.25Accuracy (%) (5-shot)47.3
Open LLM Leaderboard v1 - MMLU58.61Accuracy (%) (5-shot)43.8
Open LLM Leaderboard v1 - ARC Challenge57.85Normalized accuracy (%) (25-shot)38.3
Open LLM Leaderboard v1 - WinoGrande74.35Accuracy (%) (5-shot)36.1

Interactive version: theaggregate.ai/model?slug=zephyr-dpo-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.