zephyr-7B-beta [float16] [rev: 8af01af3d4f9]: benchmark results
Provider: HuggingFace. Access: Open.
Aggregate Rating 1393 ± 35, rank #6427 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 57.44 | MC2 (%) (0-shot) | 70 |
| Open LLM Leaderboard v1 - HellaSwag | 84.53 | Normalized accuracy (%) (10-shot) | 66.7 |
| Open LLM Leaderboard v1 - WinoGrande | 78.06 | Accuracy (%) (5-shot) | 60.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.03 | Normalized accuracy (%) (25-shot) | 55.6 |
| Open LLM Leaderboard v1 - MMLU | 61.06 | Accuracy (%) (5-shot) | 50.7 |
| Open LLM Leaderboard v1 - GSM8K | 11.37 | Accuracy (%) (5-shot) | 32.8 |
Interactive version: theaggregate.ai/model?slug=zephyr-7b-beta-float16-rev-8af01af3d4f9 · How It Works · Data refreshed daily, snapshot 2026-11-08.