DPOpenHermes-7B [bfloat16] [rev: f7742bd00c7d]: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1423 ± 33, rank #5007 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 85.96 | Normalized accuracy (%) (10-shot) | 77.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 65.7 | Normalized accuracy (%) (25-shot) | 70.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 56.95 | MC2 (%) (0-shot) | 69.1 |
| Open LLM Leaderboard v1 - GSM8K | 54.36 | Accuracy (%) (5-shot) | 66.1 |
| Open LLM Leaderboard v1 - WinoGrande | 78.61 | Accuracy (%) (5-shot) | 64.3 |
| Open LLM Leaderboard v1 - MMLU | 63.89 | Accuracy (%) (5-shot) | 63.9 |
Interactive version: theaggregate.ai/model?slug=dpopenhermes-7b-bfloat16-rev-f7742bd00c7d · How It Works · Data refreshed daily, snapshot 2026-11-08.