NVIDIA model product
Nemotron 3 Super
Nemotron 3 Super is NVIDIA’s 120B total / 12B active parameter hybrid Mamba-Attention Mixture-of-Experts model for agentic reasoning, coding, planning, tool calling, and long-context analysis.
Updated Oct 23, 2026. Default version: Nemotron 3 Super (120B A12B)
LLMBoard Score43.3Nemotron 3 Super (120B A12B)
Coverage100%23 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable
Nemotron 3 Super Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Nemotron 3 Super Benchmark Results
Benchmark scores for Nemotron 3 Super (120B A12B).
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkWMT24++ | Score86.67% | Rank01 | Participants24 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkRULER | Score91.75% | Rank02 | Participants5 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkArena-Hard v2 | Score73.88% | Rank06 | Participants19 | Percentile72.22% | EvidenceC | Evaluated |
| BenchmarkBird-SQL (dev) | Score41.80% | Rank06 | Participants9 | Percentile37.50% | EvidenceC | Evaluated |
| BenchmarkHMMT 2025 | Score94.73% | Rank08 | Participants33 | Percentile78.13% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score81.19% | Rank10 | Participants76 | Percentile88.00% | EvidenceC | Evaluated |
| BenchmarkMMLU-ProX | Score79.36% | Rank13 | Participants33 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkMulti-Challenge | Score55.23% | Rank17 | Participants34 | Percentile51.52% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score42.05% | Rank17 | Participants31 | Percentile46.67% | EvidenceC | Evaluated |
| BenchmarkTau2 Airline | Score56.25% | Rank21 | Participants26 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkAA-LCR | Score58.31% | Rank22 | Participants27 | Percentile19.23% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score25.78% | Rank22 | Participants25 | Percentile12.50% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score72.56% | Rank26 | Participants46 | Percentile44.44% | EvidenceC | Evaluated |
| BenchmarkTau2 Retail | Score62.83% | Rank26 | Participants28 | Percentile7.41% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score64.36% | Rank31 | Participants37 | Percentile16.67% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score83.73% | Rank34 | Participants142 | Percentile76.60% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score71.50% | Rank39 | Participants168 | Percentile77.25% | EvidenceB | EvaluatedN/A |
| BenchmarkSWE-bench Multilingual | Score45.78% | Rank45 | Participants50 | Percentile10.20% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score90.21% | Rank49 | Participants122 | Percentile60.33% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score31.00% | Rank52 | Participants53 | Percentile1.92% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score3.14% | Rank60 | Participants200 | Percentile70.35% | EvidenceB | EvaluatedN/A |
| BenchmarkBrowseComp | Score31.28% | Rank66 | Participants70 | Percentile5.80% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score22.82% | Rank67 | Participants109 | Percentile38.89% | EvidenceC | Evaluated |
| BenchmarkAA SciCode Subtasks | Score36.23% | Rank73 | Participants89 | Percentile18.18% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score82.70% | Rank86 | Participants256 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkAA HLE Text No Tools | Score20.76% | Rank87 | Participants200 | Percentile56.78% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score24.32% | Rank96 | Participants201 | Percentile52.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score80.00% | Rank97 | Participants199 | Percentile51.52% | EvidenceB | EvaluatedN/A |
| BenchmarkSWE-Bench Verified | Score53.73% | Rank100 | Participants120 | Percentile16.81% | EvidenceC | Evaluated |
| BenchmarkAA LCR v1.1 | Score65.67% | Rank103 | Participants193 | Percentile46.88% | EvidenceB | EvaluatedN/A |
Nemotron 3 Super Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryspanish | Rank92 | Rating / score1,417.65 | Votes352 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank110 | Rating / score1,349.79 | Votes1,219 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank111 | Rating / score1,384.09 | Votes1,323 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank113 | Rating / score1,430.85 | Votes583 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank113 | Rating / score1,439.30 | Votes1,824 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank113 | Rating / score1,407.59 | Votes3,113 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank114 | Rating / score1,403.40 | Votes279 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank114 | Rating / score1,386.50 | Votes1,416 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank114 | Rating / score1,387.79 | Votes2,202 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank115 | Rating / score1,432.67 | Votes2,823 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank115 | Rating / score1,350.97 | Votes1,679 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts | Rank117 | Rating / score1,409.50 | Votes4,381 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank117 | Rating / score1,419.02 | Votes1,725 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank118 | Rating / score1,367.13 | Votes5,381 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank118 | Rating / score1,370.58 | Votes4,702 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank118 | Rating / score1,389.44 | Votes7,844 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank119 | Rating / score1,397.91 | Votes656 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank119 | Rating / score1,391.82 | Votes552 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank119 | Rating / score1,405.42 | Votes446 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank119 | Rating / score1,368.55 | Votes2,090 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank120 | Rating / score1,388.76 | Votes352 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank121 | Rating / score1,400.23 | Votes3,158 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank122 | Rating / score1,409.26 | Votes2,832 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank123 | Rating / score1,387.46 | Votes1,221 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank123 | Rating / score1,345.56 | Votes276 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank124 | Rating / score1,386.16 | Votes4,396 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank124 | Rating / score1,396.85 | Votes1,768 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank125 | Rating / score1,377.57 | Votes7,871 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank126 | Rating / score1,403.18 | Votes1,882 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank127 | Rating / score1,345.78 | Votes5,402 | ObservationsN/A | Result date |
Nemotron 3 Super Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.05 input, $0.25 output per 1M via NanoGPT
- Tracked offerings
- 15
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderRequesty | Provider model IDnemotron-3-super-120b-a12b | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderNanoGPT | Provider model IDnvidia/nemotron-3-super-120b-a12b | Regionglobal | Input / 1M$0.05 | Output / 1M$0.25 | Context262.1K | Updated |
| ProviderKilo Gateway | Provider model IDnvidia/nemotron-3-super-120b-a12b | Regionglobal | Input / 1M$0.08 | Output / 1M$0.45 | Context262.1K | Updated |
| ProviderPioneer | Provider model IDnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | Regionglobal | Input / 1M$0.09 | Output / 1M$0.45 | Context256K | Updated |
| ProviderKenari | Provider model IDnemotron-3-super-120b-a12b | Regionglobal | Input / 1M$0.0971 | Output / 1M$0.48 | Context262.1K | Updated |
| ProviderRequesty | Provider model IDnvidia-nemotron-3-super-120b-a12b | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context262.1K | Updated |
| ProviderBoundless | Provider model IDnemotron3-super | Regionglobal | Input / 1M$0.12 | Output / 1M$0.52 | Context262.1K | Updated |
| ProviderVercel AI Gateway | Provider model IDnvidia/nemotron-3-super-120b-a12b | Regionglobal | Input / 1M$0.15 | Output / 1M$0.65 | Context256K | Updated |
| ProviderPerplexity Agent | Provider model IDnvidia/nemotron-3-super-120b-a12b | Regionglobal | Input / 1M$0.25 | Output / 1M$2.5 | Context1M | Updated |
| ProviderSynthetic | Provider model IDhf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | Regionglobal | Input / 1M$0.30 | Output / 1M$1 | Context262.1K | Updated |
| ProviderOpenRouter | Provider model IDnvidia/nemotron-3-super-120b-a12b | Regionglobal | Input / 1M$0.30 | Output / 1M$2.4 | Context262.1K | Updated |
| ProviderNebius Token Factory | Provider model IDnvidia/nemotron-3-super-120b-a12b | Regionglobal | Input / 1M$0.30 | Output / 1M$0.90 | Context262.1K | Updated |
| ProviderCrusoe | Provider model IDnvidia/NVIDIA-Nemotron-3-Super-120B-A12B | Regionglobal | Input / 1M$0.30 | Output / 1M$2.4 | Context262.1K | Updated |
| ProviderThinking Machines | Provider model IDnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144 | Regionglobal | Input / 1M$0.57 | Output / 1M$1.44 | Context262.1K | Updated |
| ProviderThinking Machines | Provider model IDnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | Regionglobal | Input / 1M$0.57 | Output / 1M$1.44 | Context65.5K | Updated |
Nemotron 3 Super Runtime Performance
Provider-specific output speed and catalog latency for Nemotron 3 Super (120B A12B). Runtime does not affect the capability score.
No runtime data
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.
Nemotron 3 Super Specifications
Technical details for the model's default version.
- Version
- Nemotron 3 Super (120B A12B)
- Released
- Mar 11, 2026
- Knowledge cutoff
- Jun 1, 2025
- Parameters
- 120B
- Context window
- 262.1K
- Max output
- 262.1K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- NVIDIA Open Model License Agreement
Nemotron 3 Super 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 |
|---|
| VersionNemotron 3 Super (120B A12B) | Released | LLMBoard43.25 | Parameters120B | Context262.1K | Max output262.1K | Open weightsYes | LicenseNVIDIA Open Model License Agreement |
Models similar to Nemotron 3 Super
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
NV
Nemotron Labs Dory 1.0
NVIDIA
NV
Nemotron 3.5 Lightning
NVIDIA
NV
Nemotron 3.5 Bolt
NVIDIA
NV
Nemotron 3 Nano
NVIDIA
NV
Nemotron Nano 9B
NVIDIA
NV
Nemotron 3.5 Super VL
NVIDIA
What is Nemotron 3 Super?
Key information about Nemotron 3 Super and its available data.
Nemotron 3 Super is a hybrid Mamba-Attention Mixture-of-Experts model with Mamba-2 layers, Transformer attention layers, LatentMoE routing, Multi-Token Prediction, and native NVFP4 pretraining on Blackwell.
It supports a 1M-token context window and was pre-trained on 25 trillion tokens and post-trained with multi-environment reinforcement learning across 21 configurations.
Data as of 2026-10-22.
FAQ
Common questions about Nemotron 3 Super.
When was Nemotron 3 Super released?
Nemotron 3 Super's default version was released on Mar 11, 2026.
How much does Nemotron 3 Super cost?
No official standard PAYG price is currently available for Nemotron 3 Super. The lowest tracked third-party offer starts at $0.05 input and $0.25 output via NanoGPT.
Who created Nemotron 3 Super?
Nemotron 3 Super was created by NVIDIA.
What is the context window for Nemotron 3 Super?
The default version has a 262.1K token context window.
Is Nemotron 3 Super open weight?
Yes. The default version is marked as open weight under NVIDIA Open Model License Agreement.