Hermes-low-tune-2 [bfloat16] [rev: 5e9fbbcf7c79]: benchmark results
A task arithmetic merge by nlpguy, with the exact parent checkpoints and interpolation recipe recorded in its release card. Provider: nlpguy. Access: Open.
Aggregate Rating 1420 ± 33, rank #5161 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 62.47 | Accuracy (%) (5-shot) | 75.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 65.27 | Normalized accuracy (%) (25-shot) | 69.6 |
| Open LLM Leaderboard v1 - HellaSwag | 84.41 | Normalized accuracy (%) (10-shot) | 65.9 |
| Open LLM Leaderboard v1 - MMLU | 63.63 | Accuracy (%) (5-shot) | 62 |
| Open LLM Leaderboard v1 - WinoGrande | 78.22 | Accuracy (%) (5-shot) | 61.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 53.12 | MC2 (%) (0-shot) | 58.5 |
Interactive version: theaggregate.ai/model?slug=hermes-low-tune-2-bfloat16-rev-5e9fbbcf7c79 · How It Works · Data refreshed daily, snapshot 2026-11-08.