zephyr-7B-sft-full [float16] [rev: 92f9fac4529a]: benchmark results
Provider: HuggingFace. Access: Open.
Aggregate Rating 1375 ± 33, rank #6986 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 60.2 | Accuracy (%) (5-shot) | 47.2 |
| Open LLM Leaderboard v1 - WinoGrande | 76.24 | Accuracy (%) (5-shot) | 47 |
| Open LLM Leaderboard v1 - GSM8K | 27.98 | Accuracy (%) (5-shot) | 45.6 |
| Open LLM Leaderboard v1 - HellaSwag | 80.83 | Normalized accuracy (%) (10-shot) | 42.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.11 | Normalized accuracy (%) (25-shot) | 39 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.74 | MC2 (%) (0-shot) | 18 |
Interactive version: theaggregate.ai/model?slug=zephyr-7b-sft-full-float16-rev-92f9fac4529a · How It Works · Data refreshed daily, snapshot 2026-11-08.