llama3-openhermes-2.5: benchmark results
Provider: sumandas. Access: Open.
Aggregate Rating 1397 ± 39, rank #6252 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 65.64 | Accuracy (%) (5-shot) | 85 |
| Open LLM Leaderboard v1 - WinoGrande | 78.3 | Accuracy (%) (5-shot) | 62 |
| Open LLM Leaderboard v1 - HellaSwag | 79.74 | Normalized accuracy (%) (10-shot) | 39 |
| Open LLM Leaderboard v1 - ARC Challenge | 57.08 | Normalized accuracy (%) (25-shot) | 36.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46 | MC2 (%) (0-shot) | 33.1 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
Interactive version: theaggregate.ai/model?slug=llama3-openhermes-2-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.