NVIDIA model product
1 Nemotron 70B is a large language model customized by NVIDIA to improve the helpfulness of generated responses.
Updated Sep 8, 2026. Default version: Llama 3.1 Nemotron 70B Instruct
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Llama 3.1 Nemotron 70B Instruct.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGSM8K Chat | Score81.88% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkInstruct HumanEval | Score73.84% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMLU Chat | Score80.58% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkXLSum English | Score31.61% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score84.53% | Rank05 | Participants22 | Percentile80.95% | EvidenceC | Evaluated |
| BenchmarkTruthfulQA | Score58.63% | Rank07 | Participants18 | Percentile64.71% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score85.58% | Rank12 | Participants27 | Percentile57.69% | EvidenceC | Evaluated |
| BenchmarkMT-Bench | Score8.99% | Rank12 | Participants12 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score69.20% | Rank23 | Participants34 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score91.43% | Rank23 | Participants48 | Percentile53.19% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score80.20% | Rank61 | Participants101 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,282.43 rating | Rank172 | Participants210 | Percentile18.18% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,298.64 rating | Rank183 | Participants210 | Percentile12.92% | EvidenceA | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryindustry mathematical | Rank157 | Rating / score1,287.27 | Votes874 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank158 | Rating / score1,300.42 | Votes392 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank161 | Rating / score1,303.02 | Votes489 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank162 | Rating / score1,314.86 | Votes3,714 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank164 | Rating / score1,268.38 | Votes1,001 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank165 | Rating / score1,262.89 | Votes723 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank165 | Rating / score1,299.94 | Votes874 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank166 | Rating / score1,271.01 | Votes1,041 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank167 | Rating / score1,261.29 | Votes904 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank168 | Rating / score1,335.85 | Votes392 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank169 | Rating / score1,293.10 | Votes1,299 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank170 | Rating / score1,242.38 | Votes453 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank171 | Rating / score1,210.76 | Votes4,748 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank171 | Rating / score1,282.72 | Votes1,136 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank171 | Rating / score1,248.74 | Votes961 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank171 | Rating / score1,278.71 | Votes1,041 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank172 | Rating / score1,282.43 | Votes7,140 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank172 | Rating / score1,327.28 | Votes489 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank173 | Rating / score1,275.55 | Votes1,227 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank173 | Rating / score1,304.66 | Votes723 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank174 | Rating / score1,266.25 | Votes1,953 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank174 | Rating / score1,283.68 | Votes2,081 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank174 | Rating / score1,329.28 | Votes3,714 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank174 | Rating / score1,295.33 | Votes453 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank175 | Rating / score1,251.94 | Votes2,959 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank176 | Rating / score1,276.05 | Votes1,001 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank178 | Rating / score1,272.09 | Votes1,312 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank178 | Rating / score1,325.86 | Votes1,136 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank178 | Rating / score1,293.21 | Votes1,227 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank179 | Rating / score1,294.61 | Votes904 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNvidia | Provider model IDnvidia/llama-3.1-nemotron-70b-instruct | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for Llama 3.1 Nemotron 70B Instruct. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionLlama 3.1 Nemotron 70B Instruct | Released | LLMBoard1.28 | Parameters70B | ContextN/A | Max outputN/A | Open weightsYes | LicenseLlama 3.1 Community License |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Llama 3.1 Nemotron 70B and its available data.
1 70B Instruct. It was trained using RLHF (REINFORCE) with HelpSteer2-Preference prompts.
Data as of 2026-09-08.
Common questions about Llama 3.1 Nemotron 70B.
Llama 3.1 Nemotron 70B's default version was released on Oct 1, 2024.
No official standard PAYG price is currently available for Llama 3.1 Nemotron 70B.
Llama 3.1 Nemotron 70B was created by NVIDIA.
A context window is not available for the default version.
Yes. The default version is marked as open weight under Llama 3.1 Community License.
1 provider offerings are linked to the default version.