Hermes 4 70B (Non-reasoning) — benchmark results
Provider: Nous Research. Released 2025-08-26. Access: Open.
Unified ELO 1507 ± 39, rank #762 of 1756 rated models, from 36 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) - Julia | 20 | Accuracy (%) | 65.4 |
| AA Omniscience - Humanities & Social Sciences | 22.7 | Accuracy (%) | 61.8 |
| AA Omniscience - Software Engineering (SWE) - PHP | 28 | Accuracy (%) | 59.7 |
| AA Omniscience - Software Engineering (SWE) - Dart | 22 | Accuracy (%) | 54.8 |
| AA Omniscience - Law | 11.3 | Accuracy (%) | 52.2 |
| AA Omniscience - Software Engineering (SWE) - R | 12 | Accuracy (%) | 52.1 |
| AA Omniscience - Health | 19.2 | Accuracy (%) | 51.5 |
| AA Omniscience - Business | 16.3 | Accuracy (%) | 48.9 |
| AA Omniscience - Software Engineering (SWE) - Python | 20 | Accuracy (%) | 48.7 |
| AA Omniscience - Software Engineering (SWE) - Swift | 36 | Accuracy (%) | 48 |
| AA-Omniscience Accuracy | 18.18 | Accuracy (%) | 45.7 |
| AA Omniscience - Software Engineering (SWE) - C | 32 | Accuracy (%) | 44 |
Interactive version: aibenchmarks.dev/model?slug=hermes-4-70b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-17.