← All benchmarks
Hermes 4 - Llama-3.1 405B (Reasoning)
Nous Research · Released 2025-08-27 · Independent benchmark scores from Artificial Analysis
Intelligence Index
9.0
Output speed
40.7
tokens/sec
Blended price
$1.50
per 1M tokens
Time to first token
0.74s
Model metadata
| Model ID | 82b207dd-d285-4a52-b2fc-2cbd27543899 |
|---|---|
| Slug | hermes-4-llama-3-1-405b-reasoning |
| Release date | 2025-08-27 |
| Provider | Nous Research |
| Provider slug | nous-research |
| Output speed | 40.7 tok/s |
| Time to first token | 0.74s |
| Time to first answer | 49.85s |
| Blended price ($/1M) | $1.50 |
| Input price ($/1M) | $1.00 |
| Output price ($/1M) | $3.00 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | 69.7% |
| artificial analysis coding index | — |
| artificial analysis intelligence index | 9.00 |
| artificial analysis math index | 69.70 |
| gpqa | 72.7% |
| hle | 10.3% |
| ifbench | 32.7% |
| lcr | 20.7% |
| livecodebench | 68.6% |
| math 500 | — |
| mmlu pro | 82.9% |
| scicode | 25.2% |
| tau banking | — |
| tau2 | 22.2% |
| terminalbench hard | 11.4% |
| terminalbench v2 1 | — |
Source: artificialanalysis.ai/models/hermes-4-llama-3-1-405b-reasoning
Benchmark data from Artificial Analysis.