NVIDIA model product
Llama 3.1 Nemotron 70B
A large language model customized by NVIDIA to improve the helpfulness of LLM generated responses.
Updated Aug 17, 2026. Default version: Llama 3.1 Nemotron 70B Instruct
LLMBoard Score2.6Llama 3.1 Nemotron 70B Instruct
Coverage80%7 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
Llama 3.1 Nemotron 70B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Llama 3.1 Nemotron 70B Benchmark Results
Benchmark scores for Llama 3.1 Nemotron 70B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGSM8K Chat | Score81.9% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkInstruct HumanEval | Score73.8% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMMLU Chat | Score80.6% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkXLSum English | Score31.6% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score84.5% | Rank05 | Participants22 | Percentile81.0% | EvidenceC | Evaluated |
| BenchmarkTruthfulQA | Score58.6% | Rank07 | Participants18 | Percentile64.7% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score85.6% | Rank12 | Participants27 | Percentile57.7% | EvidenceC | Evaluated |
| BenchmarkMT-Bench | Score9.0% | Rank12 | Participants12 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score69.2% | Rank23 | Participants34 | Percentile33.3% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score91.4% | Rank23 | Participants48 | Percentile53.2% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score80.2% | Rank61 | Participants101 | Percentile40.0% | EvidenceC | Evaluated |
Llama 3.1 Nemotron 70B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryoverall | Rank239 | Rating / score1282.8 | Votes7,140 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank262 | Rating / score1299.0 | Votes7,140 | ObservationsN/A | Result date |
Llama 3.1 Nemotron 70B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.60 input, $0.60 output per 1M via Eden AI
- Tracked offerings
- 2
Sort by
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 |
| ProviderEden AI | Provider model IDdeepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct | Regionglobal | Input / 1M$0.60 | Output / 1M$0.60 | Context131.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Llama 3.1 Nemotron 70B Runtime Performance
Provider-specific output speed and catalog latency for Llama 3.1 Nemotron 70B Instruct. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo 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.
Llama 3.1 Nemotron 70B Specifications
Technical details for the model's default version.
- Version
- Llama 3.1 Nemotron 70B Instruct
- Released
- Oct 1, 2024
- Knowledge cutoff
- Dec 1, 2023
- Parameters
- 70B
- Context window
- 128K
- Max output
- 8.2K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Llama 3.1 Community License
Llama 3.1 Nemotron 70B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionLlama 3.1 Nemotron 70B Instruct | Released | LLMBoard2.6 | Parameters70B | Context128K | Max output8.2K | Open weightsYes | LicenseLlama 3.1 Community License |
Llama 3.1 Nemotron 70B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Llama 3.1 Nemotron 70B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
NV
Llama 3.1 Nemotron Nano 8B
NVIDIA
NV
Llama 3.3 Nemotron Super 49B
NVIDIA
NV
Llama 3.1 Nemotron Ultra 253B
NVIDIA
NV
Nemotron Nano 9B
NVIDIA
NV
Nemotron 3 Nano
NVIDIA
NV
Nemotron 3.5 Lightning
NVIDIA
What is Llama 3.1 Nemotron 70B?
Key information about Llama 3.1 Nemotron 70B and its available data.
A large language model customized by NVIDIA to improve the helpfulness of LLM generated responses. 1 70B Instruct. The model was trained using RLHF (REINFORCE) with HelpSteer2-Preference prompts.
Data as of 2026-08-17.
FAQ
Common questions about Llama 3.1 Nemotron 70B.
When was Llama 3.1 Nemotron 70B released?
Llama 3.1 Nemotron 70B's default version was released on Oct 1, 2024.
How much does Llama 3.1 Nemotron 70B cost?
No official standard PAYG price is currently available for Llama 3.1 Nemotron 70B. The lowest tracked third-party offer starts at $0.60 input and $0.60 output via Eden AI.
Who created Llama 3.1 Nemotron 70B?
Llama 3.1 Nemotron 70B was created by NVIDIA.
What is the context window for Llama 3.1 Nemotron 70B?
The default version has a 128K token context window.
Is Llama 3.1 Nemotron 70B open weight?
Yes. The default version is marked as open weight under Llama 3.1 Community License.
How many API providers offer Llama 3.1 Nemotron 70B?
2 provider offerings are linked to the default version.
What models should I compare Llama 3.1 Nemotron 70B with?
Nearby ranked alternatives include Granite 3.3 8B, Qwen3.5 2B, Gemini Diffusion.