zephyr-7B-beta [bfloat16] [rev: 8af01af3d4f9]: benchmark results

Provider: HuggingFace. Access: Open.

Aggregate Rating 1396 ± 33, rank #6285 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC257.45MC2 (%) (0-shot)70
Open LLM Leaderboard v1 - HellaSwag84.36Normalized accuracy (%) (10-shot)65.6
Open LLM Leaderboard v1 - WinoGrande77.74Accuracy (%) (5-shot)58.2
Open LLM Leaderboard v1 - ARC Challenge62.03Normalized accuracy (%) (25-shot)55.6
Open LLM Leaderboard v1 - MMLU61.07Accuracy (%) (5-shot)50.7
Open LLM Leaderboard v1 - GSM8K29.04Accuracy (%) (5-shot)46.5

Interactive version: theaggregate.ai/model?slug=zephyr-7b-beta-bfloat16-rev-8af01af3d4f9 · How It Works · Data refreshed daily, snapshot 2026-11-08.