Nvidia's latest Llama fine-tune optimized for instruction following. Early results hints that it might outperform models such as GPT-4o and Claude 3.5 Sonnet.
Added Apr 15, 2025
Context Window
16.4K
Max Output
8.2K
Input Price (Auto)
$0.36/1M
Output Price (Auto)
$0.41/1M
Cache Read (Auto)
$0.18/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
8.5
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
51.5%
Better than 30% of models compared
HLE
Humanity's Last Exam
4.2%
Better than 17% of models compared
IFBench
Instruction-following benchmark
39.0%
Better than 37% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
19.0%
Better than 17% of models compared
AA-LCR
Long context reasoning evaluation
24.3%
Better than 39% of models compared
Coding
SciCode
Python programming for scientific computing
29.9%
Better than 46% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
6.8%
Better than 38% of models compared
LiveCodeBench
Contamination-free coding benchmark
30.5%
Better than 36% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
3.0%
Better than 4% of models compared
AIME
American Invitational Mathematics Examination
21.3%
Better than 48% of models compared
Math-500
Diverse mathematical problem solving benchmark
70.3%
Better than 30% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
73.2%
Better than 43% of models compared
Last updated Jun 28, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Nvidia Nemotron 70b with similar models from the same provider or model family.
Nvidia Nemotron Super 49B
nvidia/Llama-3.3-Nemotron-Super-49B-v1Llama-3.3-Nemotron-Super-49B-v1 is a model which offers a great tradeoff between model accuracy and efficiency. Efficiency (throughput) directly translates to savings. Using a novel Neural Architecture Search (NAS) approach, we greatly reduce the model's memory footprint, enabling larger workloads, as well as fitting the model on a single GPU at high workloads (H200). This NAS approach enables the selection of a desired point in the accuracy-efficiency tradeoff. For more information on the NAS approach, please refer to this paper.
Nvidia Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightningNvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. Thinking is disabled on this variant. Included in the NanoGPT subscription.
Nvidia Nemotron 3.5 Lightning Thinking
nvidia/nemotron-3.5-lightning:thinkingNvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. This variant enables its reasoning trace. Included in the NanoGPT subscription.
Nvidia Nemotron 3 Ultra 550B
nvidia/nemotron-3-ultra-550b-a55bNvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context.
Nvidia Nemotron 3 Ultra 550B Thinking
nvidia/nemotron-3-ultra-550b-a55b:thinkingNvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context. Thinking enabled.
Nvidia Nemotron 3 Nano Omni
nvidia/nemotron-3-nano-omni-30b-a3b-reasoningNvidia's Nemotron 3 Nano Omni 30B-A3B reasoning model. It accepts multimodal context on supported providers and returns text responses for perception and agentic workflows.