Hermes-low-tune-2 [float16] [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 1421 ± 33, rank #5138 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 63.53 | Accuracy (%) (5-shot) | 77 |
| Open LLM Leaderboard v1 - ARC Challenge | 65.61 | Normalized accuracy (%) (25-shot) | 70.5 |
| Open LLM Leaderboard v1 - HellaSwag | 84.47 | Normalized accuracy (%) (10-shot) | 66.3 |
| Open LLM Leaderboard v1 - MMLU | 63.69 | Accuracy (%) (5-shot) | 62.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 53.18 | MC2 (%) (0-shot) | 58.8 |
| Open LLM Leaderboard v1 - WinoGrande | 77.74 | Accuracy (%) (5-shot) | 58.2 |
Interactive version: theaggregate.ai/model?slug=hermes-low-tune-2-float16-rev-5e9fbbcf7c79 · How It Works · Data refreshed daily, snapshot 2026-11-08.