Hermes-3-Llama-3.1-8B: benchmark results
Nous Research's Hermes 3 fine-tune of Llama 3.1 8B, a steerable generalist assistant with function calling, JSON mode and roleplay focus (August 2024). Provider: Nous Research. Released 2024-07-28. Access: Open.
Aggregate Rating 1450 ± 18, rank #997 of 1656 rated models, from 107 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LatamBoard - FLORES Bidirectional | 45.94 | Score (%) | 90.9 |
| LatamBoard - Translation Score | 46.55 | Score (%) | 90.9 |
| Open PL LLM - KLEJ NER (multiple choice, 5-shot) | 54.96 | Accuracy (%) | 84.4 |
| LatamBoard - Spanish WNLI | 76.06 | Score (%) | 83.3 |
| LatamBoard - Spanish Escola | 70.85 | Score (%) | 81.8 |
| LatamBoard - Spanish OpenBookQA | 37.2 | Score (%) | 81.8 |
| Open PL LLM - PolEmo2-OUT (multiple choice, 5-shot) | 75.51 | Accuracy (%) | 79.9 |
| LatamBoard - Spanish COPA | 83.4 | Score (%) | 78.8 |
| LatamBoard - Spanish XNLI | 47.67 | Score (%) | 75.8 |
| Open LLM Leaderboard - MuSR | 43.69 | Score | 75.7 |
| Open PL LLM - PSC (generative, 5-shot) | 96.14 | Binary F1 (%) | 74.6 |
| Open LLM Leaderboard - IFEval | 61.7 | Score | 73.8 |
Interactive version: theaggregate.ai/model?slug=hermes-3-llama-3-1-8b · How It Works · Data refreshed daily, snapshot 2026-10-20.