← All benchmarks
Hermes 4 - Llama-3.1 70B (Non-reasoning)
Nous Research · Released 2025-08-27 · Independent benchmark scores from Artificial Analysis
Intelligence Index
6.9
Output speed
98.1
tokens/sec
Blended price
$0.20
per 1M tokens
Time to first token
0.59s
Model metadata
| Model ID | 235060f4-057d-4bd1-8b8e-4a92908c770e |
|---|---|
| Slug | hermes-4-llama-3-1-70b |
| Release date | 2025-08-27 |
| Provider | Nous Research |
| Provider slug | nous-research |
| Output speed | 98.1 tok/s |
| Time to first token | 0.59s |
| Time to first answer | 0.59s |
| Blended price ($/1M) | $0.20 |
| Input price ($/1M) | $0.13 |
| Output price ($/1M) | $0.40 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | 11.3% |
| artificial analysis coding index | — |
| artificial analysis intelligence index | 6.90 |
| artificial analysis math index | 11.30 |
| gpqa | 49.1% |
| hle | 3.6% |
| ifbench | 29.0% |
| lcr | 2.0% |
| livecodebench | 26.9% |
| math 500 | — |
| mmlu pro | 66.4% |
| scicode | 27.7% |
| tau banking | — |
| tau2 | 21.6% |
| terminalbench hard | 0.0% |
| terminalbench v2 1 | — |
Source: artificialanalysis.ai/models/hermes-4-llama-3-1-70b
Benchmark data from Artificial Analysis.