llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1224 models729 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

NVIDIA model product

Nemotron 3 Nano

6B hybrid MoE large language model from NVIDIA with a 1M-token context window.

Updated Sep 8, 2026. Default version: Nemotron 3 Nano (30B A3B)

LLMBoard Score34.2Nemotron 3 Nano (30B A3B)
Coverage40%15 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Nemotron 3 Nano Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Nemotron 3 Nano (30B A3B) LLMBoard score breakdown

Nemotron 3 Nano Benchmark Results

Benchmark scores for Nemotron 3 Nano (30B A3B).

18 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkWMT24++Score86.20%Rank02Participants23Percentile95.45%EvidenceCEvaluatedSep 8, 2026
BenchmarkArena-Hard v2Score67.70%Rank09Participants19Percentile55.56%EvidenceCEvaluatedSep 8, 2026
BenchmarkAIME 2025Score99.20%Rank10Participants119Percentile92.37%EvidenceCEvaluatedSep 8, 2026
BenchmarkTau2 AirlineScore48.00%Rank21Participants24Percentile13.04%EvidenceCEvaluatedSep 8, 2026
BenchmarkSciCodeScore33.30%Rank22Participants24Percentile8.70%EvidenceCEvaluatedSep 8, 2026
BenchmarkMulti-ChallengeScore38.50%Rank24Participants29Percentile17.86%EvidenceCEvaluatedSep 8, 2026
BenchmarkTerminal-BenchScore8.50%Rank24Participants25Percentile4.17%EvidenceCEvaluatedSep 8, 2026
BenchmarkMMLU-ProXScore59.50%Rank25Participants32Percentile22.58%EvidenceCEvaluatedSep 8, 2026
BenchmarkTau2 RetailScore56.90%Rank27Participants27Percentile0.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkTau2 TelecomScore42.20%Rank34Participants36Percentile5.71%EvidenceCEvaluatedSep 8, 2026
BenchmarkLiveCodeBench v6Score68.30%Rank42Participants62Percentile32.79%EvidenceCEvaluatedSep 8, 2026
BenchmarkMMLU-ProScore78.30%Rank63Participants138Percentile54.74%EvidenceCEvaluatedSep 8, 2026
BenchmarkHumanity's Last ExamScore15.50%Rank79Participants103Percentile23.53%EvidenceCEvaluatedSep 8, 2026
BenchmarkSWE-Bench VerifiedScore38.80%Rank105Participants113Percentile7.14%EvidenceCEvaluatedSep 8, 2026
BenchmarkGPQAScore75.00%Rank118Participants247Percentile52.44%EvidenceCEvaluatedSep 8, 2026
BenchmarkLM Arena Text FactualityScore1,362.71 ratingRank118Participants121Percentile2.50%EvidenceAEvaluatedSep 2, 2026
BenchmarkLM Arena TextScore1,348.22 ratingRank138Participants210Percentile34.45%EvidenceAEvaluatedSep 2, 2026
BenchmarkLM Arena Text Style ControlScore1,314.23 ratingRank174Participants210Percentile17.22%EvidenceAEvaluatedSep 2, 2026

Nemotron 3 Nano Arena Results

Preference and agent-evaluation results for the default version.

30 of 78 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
Arenatext factualityCategorymathRank77Rating / score1,383.55Votes597ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategorychineseRank78Rating / score1,398.75Votes691ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryindustry legal and governmentRank80Rating / score1,358.21Votes678ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryrussianRank90Rating / score1,336.54Votes1,185ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryindustry life and physical and social scienceRank98Rating / score1,377.43Votes1,588ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategorycreative writingRank101Rating / score1,306.00Votes1,410ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategorymulti turnRank103Rating / score1,345.66Votes1,686ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryindustry entertainment and sports and mediaRank104Rating / score1,323.71Votes1,818ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryfrenchRank105Rating / score1,397.45Votes366ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryindustry business and management and financial operationsRank107Rating / score1,367.33Votes1,864ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryhard prompts englishRank109Rating / score1,404.67Votes2,117ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryspanishRank110Rating / score1,377.17Votes353ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategorycodingRank110Rating / score1,416.70Votes2,090ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryindustry software and it servicesRank112Rating / score1,403.34Votes3,935ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryindustry writing and literature and languageRank112Rating / score1,315.47Votes2,246ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryenglishRank113Rating / score1,392.76Votes5,815ObservationsN/AResult dateSep 2, 2026
ArenatextCategorygermanRank114Rating / score1,350.39Votes291ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryinstruction followingRank114Rating / score1,333.07Votes2,904ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategorylonger queryRank115Rating / score1,339.75Votes2,665ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryhard promptsRank116Rating / score1,377.23Votes7,915ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryexclude tiesRank117Rating / score1,330.46Votes10,606ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategorynon englishRank117Rating / score1,335.23Votes8,823ObservationsN/AResult dateSep 2, 2026
Arenatext factualityCategoryoverallRank118Rating / score1,362.71Votes15,050ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryjapaneseRank122Rating / score1,267.40Votes139ObservationsN/AResult dateSep 2, 2026
ArenatextCategorychineseRank124Rating / score1,386.50Votes1,251ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryindustry mathematicalRank125Rating / score1,377.27Votes669ObservationsN/AResult dateSep 2, 2026
ArenatextCategorykoreanRank127Rating / score1,268.72Votes236ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryenglishRank128Rating / score1,378.30Votes6,309ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryhard prompts englishRank128Rating / score1,376.52Votes3,273ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryindustry software and it servicesRank128Rating / score1,382.65Votes5,122ObservationsN/AResult dateSep 2, 2026

Nemotron 3 Nano 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, $0.20 output per 1M via Deep Infra
Tracked offerings
10
9 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderNvidiaProvider model IDnvidia/nemotron-3-nano-30b-a3bRegionglobalInput / 1MN/AOutput / 1MN/AContext131.1KUpdatedSep 8, 2026
ProviderKenariProvider model IDnemotron-3-nano-30b-a3bRegionglobalInput / 1MN/AOutput / 1MN/AContext262.1KUpdatedSep 8, 2026
ProviderDeep InfraProvider model IDnvidia/Nemotron-3-Nano-30B-A3BRegionglobalInput / 1M$0.05Output / 1M$0.20Context262.1KUpdatedSep 8, 2026
ProviderOpenRouterProvider model IDnvidia/nemotron-3-nano-30b-a3bRegionglobalInput / 1M$0.05Output / 1M$0.20Context262.1KUpdatedSep 8, 2026
ProviderVercel AI GatewayProvider model IDnvidia/nemotron-3-nano-30b-a3bRegionglobalInput / 1M$0.05Output / 1M$0.24Context262.1KUpdatedSep 8, 2026
ProviderKilo GatewayProvider model IDnvidia/nemotron-3-nano-30b-a3bRegionglobalInput / 1M$0.05Output / 1M$0.20Context262.1KUpdatedSep 8, 2026
ProviderPioneerProvider model IDnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16RegionglobalInput / 1M$0.05Output / 1M$0.20Context262.1KUpdatedSep 8, 2026
ProviderCrusoeProvider model IDnvidia/NVIDIA-Nemotron-3-Nano-30B-A3BRegionglobalInput / 1M$0.05Output / 1M$0.20Context262.1KUpdatedSep 8, 2026
ProviderNanoGPTProvider model IDnvidia/nemotron-3-nano-30b-a3bRegionglobalInput / 1M$0.17Output / 1M$0.68Context262.1KUpdatedSep 8, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Nemotron 3 Nano Runtime Performance

Provider-specific output speed and catalog latency for Nemotron 3 Nano (30B A3B). 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 Nano Specifications

Technical details for the model's default version.

Version
Nemotron 3 Nano (30B A3B)
Released
Dec 15, 2025
Knowledge cutoff
Nov 28, 2025
Parameters
32B
Context window
262.1K
Max output
262.1K
Inputs
text
Outputs
text
Open weights
Yes
License
NVIDIA Open Model License Agreement

Nemotron 3 Nano Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionNemotron 3 Nano (30B A3B)ReleasedDec 15, 2025LLMBoard34.19Parameters32BContext262.1KMax output262.1KOpen weightsYesLicenseNVIDIA Open Model License Agreement

Models similar to Nemotron 3 Nano

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#178-2.83
NV

Nemotron Nano 9B

NVIDIA

31.36 LLMBoard

Details
#155+3.08
NV

Nemotron 3.5 Lightning

NVIDIA

37.27 LLMBoard

Details
#185-4.77
NV

Llama 3.1 Nemotron Ultra 253B

NVIDIA

29.42 LLMBoard

Details
#123+10.09
NV

Nemotron 3 Super

NVIDIA

44.28 LLMBoard

Details
#208-12.66
NV

Llama 3.3 Nemotron Super 49B

NVIDIA

21.53 LLMBoard

Details
#247-25.65
NV

Llama 3.1 Nemotron Nano 8B

NVIDIA

8.54 LLMBoard

Details

What is Nemotron 3 Nano?

Key information about Nemotron 3 Nano and its available data.

6B active parameters per token. It supports Reasoning ON/OFF and a thinking budget, and was released on Dec 15, 2025 under the NVIDIA Open Model License.

Data as of 2026-09-08.

FAQ

Common questions about Nemotron 3 Nano.

When was Nemotron 3 Nano released?

Nemotron 3 Nano's default version was released on Dec 15, 2025.

How much does Nemotron 3 Nano cost?

No official standard PAYG price is currently available for Nemotron 3 Nano. The lowest tracked third-party offer starts at $0.05 input and $0.20 output via Deep Infra.

Who created Nemotron 3 Nano?

Nemotron 3 Nano was created by NVIDIA.

What is the context window for Nemotron 3 Nano?

The default version has a 262.1K token context window.

Is Nemotron 3 Nano open weight?

Yes. The default version is marked as open weight under NVIDIA Open Model License Agreement.

How many API providers offer Nemotron 3 Nano?

10 provider offerings are linked to the default version.

Browse runtime rankings