Hermes 4 405B (Thinking) — benchmark results
Provider: Nous Research. Released 2025-08-26. Access: Open.
Unified ELO 1639 ± 32, rank #392 of 1756 rated models, from 36 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Humanities & Social Sciences | 32.8 | Accuracy (%) | 82.9 |
| AA Omniscience - Health | 31 | Accuracy (%) | 82.5 |
| AA MMLU-Pro | 82.9 | Accuracy (%) | 82.3 |
| AA Omniscience - Business | 27 | Accuracy (%) | 80.8 |
| AA Omniscience - Law | 24.3 | Accuracy (%) | 80.8 |
| AA-Omniscience Accuracy | 30.17 | Accuracy (%) | 79.8 |
| AA Omniscience - Science, Engineering & Mathematics | 35.1 | Accuracy (%) | 77.1 |
| AA LiveCodeBench | 68.57 | Pass@1 (%) | 76.9 |
| AA Omniscience - Software Engineering (SWE) - Julia | 28 | Accuracy (%) | 75.6 |
| AA Omniscience - Software Engineering (SWE) - R | 26 | Accuracy (%) | 74.6 |
| AA Omniscience - Software Engineering (SWE) - HTML | 44 | Accuracy (%) | 72.1 |
| AA Omniscience - Software Engineering (SWE) - Swift | 48 | Accuracy (%) | 70 |
Interactive version: aibenchmarks.dev/model?slug=hermes-4-405b-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-17.