Hermes 4 405B (Thinking): benchmark results
Provider: Nous Research. Released 2025-08-26. Access: Open.
Unified ELO 1556 ± 1, rank #610 of 1761 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SpeechMap Compliance | 89.7 | % Requests Completed | 90.5 |
| AA Omniscience - Software Engineering (SWE) - R | 26 | Accuracy (%) | 85.5 |
| AA Omniscience - Software Engineering (SWE) - Julia | 28 | Accuracy (%) | 85.2 |
| AA Omniscience - Software Engineering (SWE) - HTML | 46 | Accuracy (%) | 83.1 |
| AA Omniscience - Software Engineering (SWE) - Swift | 48 | Accuracy (%) | 82.4 |
| CritPt | 30 | Accuracy (self-reported) | 80.8 |
| AA MMLU-Pro | 82.9 | Accuracy (%) | 80.7 |
| AA Omniscience - Software Engineering (SWE) - C | 49 | Accuracy (%) | 79.9 |
| AA Omniscience - Humanities & Social Sciences | 31.7 | Accuracy (%) | 77.5 |
| AA Omniscience - Health | 31.6 | Accuracy (%) | 77 |
| AA Omniscience - Business | 26.1 | Accuracy (%) | 76 |
| AA Omniscience - Law | 24.3 | Accuracy (%) | 75.9 |
Interactive version: theaggregate.ai/model?slug=hermes-4-405b-thinking · How It Works · Data refreshed daily, snapshot 2026-09-05.