DeepHermes 3 - Llama-3.1 8B Preview: benchmark results
Provider: Nous Research. Released 2025-01-15.
Aggregate Rating 1364 ± 41, rank #7339 of 10916 rated models, from 5 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Humanity's Last Exam | 4.26 | Accuracy (%) | 17 |
| AA LiveCodeBench | 8.47 | Pass@1 (%) | 6.1 |
| AA MMLU-Pro | 36.53 | Accuracy (%) | 5.2 |
| AA GPQA Diamond | 26.97 | Accuracy (%) | 3.7 |
| AA MATH-500 | 21.8 | Accuracy (%) | 0 |
Interactive version: theaggregate.ai/model?slug=deephermes-3-llama-3-1-8b-preview · How It Works · Data refreshed daily, snapshot 2026-11-08.