alignment-handbook-zephyr-7b_ppostep_100: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1096 ± 39, rank #10761 of 10916 rated models, from 5 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - ARC Challenge | 29.27 | Normalized accuracy (%) (25-shot) | 8.4 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - MMLU | 23.76 | Accuracy (%) (5-shot) | 2.4 |
| Open LLM Leaderboard v1 - HellaSwag | 25.87 | Normalized accuracy (%) (10-shot) | 2 |
| Open LLM Leaderboard v1 - WinoGrande | 48.93 | Accuracy (%) (5-shot) | 0.8 |
Interactive version: theaggregate.ai/model?slug=alignment-handbook-zephyr-7b-ppostep-100 · How It Works · Data refreshed daily, snapshot 2026-11-08.