Llama 3.1 Nemotron 70B Instruct
Unavailable in this round
Language model
Llama 3.1 Nemotron 70B Instruct
NVIDIA
- Released
- April 15, 2025
- Data date
- September 26, 2026
- Input
- Text
- Output
- Text
Llama 3.1 Nemotron 70B Instruct is NVIDIA’s post-trained Llama 3.1 variant with 70 billion parameters and a 128,000-token context.
The model handles text and supports tool calls. Its open release uses the Llama 3.1 Community License rather than NVIDIA's Open Model License. A product deployment therefore follows different usage terms from NVIDIA's Open Model License. This is an instruct checkpoint, neither a base model nor a later Nemotron generation.
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
Arena Hard (Show measurement, test conditions, and source)
- Source value
- 85
- Score
- 85
- Metric
- unknown
- Unit
- No unit provided
- Direction
- Higher is better
- Confidence interval
- 1.5
- Source type
- vendor-reported
- Evaluator
- NVIDIA Llama-3.1-Nemotron-70B-Instruct-HF model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact 70B Instruct checkpoint; card reports a 95% confidence interval of ±1.5 but does not identify the eval prompt, judge, or score unit.
AlpacaEval 2 LC (Show measurement, test conditions, and source)
- Source value
- 57.6
- Score
- 57.6
- Metric
- unknown
- Unit
- No unit provided
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- NVIDIA Llama-3.1-Nemotron-70B-Instruct-HF model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact 70B Instruct checkpoint; card reports standard error 1.65 for the length-controlled result. Score unit is not labeled.
MT-Bench (Show measurement, test conditions, and source)
- Source value
- 8.98
- Score
- 8.98
- Metric
- unknown
- Unit
- No unit provided
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- NVIDIA Llama-3.1-Nemotron-70B-Instruct-HF model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact 70B Instruct checkpoint; card identifies GPT-4-Turbo as judge; remaining prompt and sampling configuration are not stated.
Our tests
SVG short test
One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.
Popularity
22.2 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Input | Documented modalities. Retrieved September 26, 2026. |
| Output | Documented modalities. Retrieved September 26, 2026. |
| Research status | Research date October 15, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not published | benchmark-snapshot-and-protocol Note The exact 70B card omits evaluation dates and most prompting/sampling details; reported uncertainty for AlpacaEval is standard error, not a confidence interval. |
| Additional source | NVIDIA Llama 3.1 Nemotron 70B Instruct model card (retrieved October 2, 2026; October 15, 2026) · NVIDIA Llama 3.1 Nemotron 70B model card · Editorial description reviewed October 2, 2026 |
| Additional source | Meta Llama 3.1 license · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |