Hermes 4 405B (Non-reasoning) — benchmark results
Provider: Nous Research. Released 2025-08-26. Access: Open.
Unified ELO 1577 ± 37, rank #541 of 1776 rated models, from 36 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Humanities & Social Sciences | 30 | Accuracy (%) | 79.6 |
| AA Omniscience - Law | 21.7 | Accuracy (%) | 77.8 |
| AA Omniscience - Health | 28.5 | Accuracy (%) | 77.6 |
| AA Omniscience - Business | 24.3 | Accuracy (%) | 76.2 |
| AA-Omniscience Accuracy | 26.27 | Accuracy (%) | 72.1 |
| AA Omniscience - Software Engineering (SWE) - Julia | 24 | Accuracy (%) | 70.4 |
| AA Omniscience - Software Engineering (SWE) - Rust | 56 | Accuracy (%) | 64.3 |
| AA Omniscience - Software Engineering (SWE) - Swift | 44 | Accuracy (%) | 63.3 |
| AA Omniscience - Software Engineering (SWE) - Go | 22 | Accuracy (%) | 62.2 |
| AA LiveCodeBench | 54.6 | Pass@1 (%) | 61.5 |
| AA Omniscience | -33 | Score | 60.9 |
| AA Omniscience - Software Engineering (SWE) - R | 16 | Accuracy (%) | 60.8 |
Interactive version: theaggregate.ai/model?slug=hermes-4-405b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.