zephyr-0.2-a2.5: benchmark results
Provider: HuggingFace. Access: Open.
Aggregate Rating 1378 ± 37, rank #6921 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 60.19 | MC2 (%) (0-shot) | 75.4 |
| Open LLM Leaderboard v1 - HellaSwag | 83.85 | Normalized accuracy (%) (10-shot) | 62 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.77 | Normalized accuracy (%) (25-shot) | 54.4 |
| Open LLM Leaderboard v1 - MMLU | 58.33 | Accuracy (%) (5-shot) | 43.2 |
| Open LLM Leaderboard v1 - WinoGrande | 73.4 | Accuracy (%) (5-shot) | 31.9 |
| Open LLM Leaderboard v1 - GSM8K | 0.3 | Accuracy (%) (5-shot) | 11.4 |
Interactive version: theaggregate.ai/model?slug=zephyr-0-2-a2-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.