Nous Research model product
Hermes 3 70B is Nous Research's flagship instruction-following model, fine-tuned for advanced reasoning, creative writing, and complex task completion. It features exceptional instruction adherence and strong performance across multiple domains.
Updated Aug 10, 2026. Default version: Hermes 3 70B
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version Hermes 3 70B.
| BoolQ | 0.9 | 1 | 10 | 100.0% | C | |
| MuSR | 0.5 | 2 | 2 | 0.0% | C | |
| PIQA | 0.8 | 2 | 11 | 90.0% | C | |
| ARC-E | 0.8 | 3 | 8 | 71.4% | C | |
| IFBench | 0.8 | 3 | 28 | 92.6% | C | |
| AGIEval | 0.6 | 4 | 10 | 66.7% | C | |
| MT-Bench | 9.0 | 4 | 12 | 72.7% | C | |
| OpenBookQA | 0.5 | 5 | 5 | 0.0% | C | |
| TruthfulQA | 0.6 | 6 | 18 | 70.6% | C | |
| HellaSwag | 0.9 | 7 | 27 | 76.9% | C | |
| Winogrande | 0.8 | 7 | 22 | 71.4% | C | |
| BBH | 0.7 | 11 | 12 | 9.1% | C | |
| ARC-C | 0.7 | 27 | 34 | 21.2% | C | |
| MMLU | 0.8 | 66 | 100 | 34.3% | C | |
| MATH | 0.2 | 70 | 71 | 1.4% | C | |
| MMLU-Pro | 0.5 | 118 | 129 | 8.6% | C | |
| GPQA | 0.7 | 144 | 233 | 38.4% | C |
Preference and agent-evaluation signals from published Arena datasets.
The default version has no published Arena rows, or its source alias has not been resolved.
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| NanoGPT | NousResearch/hermes-3-llama-3.1-70b | global | $0.408 | $0.408 | 65.5K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| Hermes 3 70B | 40.2 | 70B | 131.1K | 16.4K | No | Apache 2.0 |
A concise description based on the published model registry.
Hermes 3 70B is Nous Research's flagship instruction-following model, fine-tuned for advanced reasoning, creative writing, and complex task completion. It features exceptional instruction adherence and strong performance across multiple domains.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about Hermes 3 70B.
Hermes 3 70B's default version was released on Aug 15, 2024.
No official standard PAYG price is currently available for Hermes 3 70B. The lowest tracked third-party offer starts at $0.408 input and $0.408 output via NanoGPT.
Hermes 3 70B is published under Nous Research in the model registry.
The default version has a 131.1K token context window.
No. The default version is not marked as having publicly available weights.
1 published provider offerings are linked to the default version.
Nearby ranked alternatives include Claude Haiku 3.5, Qwen3 VL 30B A3B Thinking, Qwen3 Max.