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
1450 models809 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

Llama 3.3 Nemotron Super 49B

3 Nemotron Super 49B is an NVIDIA model for reasoning, coding, and specialized AI agents.

Updated Nov 18, 2026. Default version: Llama 3.3 Nemotron Super 49B v1.5

LLMBoard Score20.0Llama-3.3 Nemotron Super 49B v1
Coverage80%7 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable

On this page

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

Llama 3.3 Nemotron Super 49B Capability Profile

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

Llama-3.3 Nemotron Super 49B v1 LLMBoard score breakdown

Llama 3.3 Nemotron Super 49B Benchmark Results

Benchmark scores for Llama-3.3 Nemotron Super 49B v1.

16 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkMBPPScore91.30%Rank02Participants33Percentile96.88%EvidenceCEvaluatedNov 17, 2026
BenchmarkMT-BenchScore91.70%Rank02Participants13Percentile91.67%EvidenceCEvaluatedNov 17, 2026
BenchmarkBFCL v2Score73.70%Rank03Participants5Percentile50.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkArena HardScore88.30%Rank05Participants27Percentile84.62%EvidenceCEvaluatedNov 17, 2026
BenchmarkMATH-500Score96.60%Rank13Participants33Percentile62.50%EvidenceCEvaluatedNov 17, 2026
BenchmarkAA AIME 2025Score54.67%Rank55Participants96Percentile43.16%EvidenceBEvaluatedN/A
BenchmarkAIME 2025Score58.40%Rank105Participants123Percentile14.75%EvidenceCEvaluatedNov 17, 2026
BenchmarkAA IFBenchScore38.10%Rank124Participants168Percentile26.35%EvidenceBEvaluatedN/A
BenchmarkAA CritPtScore0.00%Rank131Participants200Percentile34.67%EvidenceBEvaluatedN/A
BenchmarkAA GPQA DiamondScore64.34%Rank148Participants199Percentile25.76%EvidenceBEvaluatedN/A
BenchmarkAA Omniscience AccuracyScore17.10%Rank151Participants201Percentile25.00%EvidenceBEvaluatedN/A
BenchmarkAA HLE Text No ToolsScore5.62%Rank153Participants200Percentile23.62%EvidenceBEvaluatedN/A
BenchmarkAA LCR v1.1Score18.33%Rank167Participants193Percentile13.54%EvidenceBEvaluatedN/A
BenchmarkGPQAScore66.67%Rank168Participants265Percentile36.74%EvidenceCEvaluatedNov 17, 2026
BenchmarkLM Arena TextScore1,308.43 ratingRank170Participants221Percentile23.18%EvidenceAEvaluatedNov 11, 2026
BenchmarkLM Arena Text Style ControlScore1,327.80 ratingRank174Participants221Percentile21.36%EvidenceAEvaluatedNov 11, 2026

Llama 3.3 Nemotron Super 49B Arena Results

Preference and agent-evaluation results for the default version.

30 of 48 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenatextCategoryjapaneseRank124Rating / score1,300.71Votes418ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry mathematicalRank126Rating / score1,397.89Votes182ObservationsN/AResult dateNov 11, 2026
ArenatextCategorymathRank128Rating / score1,394.29Votes193ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryindustry mathematicalRank131Rating / score1,401.50Votes182ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorymathRank133Rating / score1,389.10Votes193ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryjapaneseRank134Rating / score1,298.02Votes418ObservationsN/AResult dateNov 11, 2026
ArenatextCategorypolishRank138Rating / score1,323.01Votes397ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry medicine and healthcareRank139Rating / score1,367.33Votes195ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry life and physical and social scienceRank144Rating / score1,367.59Votes593ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryindustry medicine and healthcareRank147Rating / score1,381.60Votes195ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry legal and governmentRank148Rating / score1,348.88Votes231ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryrussianRank148Rating / score1,333.90Votes201ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorycodingRank148Rating / score1,403.58Votes652ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryindustry life and physical and social scienceRank149Rating / score1,377.41Votes593ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorypolishRank149Rating / score1,316.15Votes397ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryindustry software and it servicesRank150Rating / score1,388.10Votes1,179ObservationsN/AResult dateNov 11, 2026
ArenatextCategorycreative writingRank152Rating / score1,305.66Votes369ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryexpertRank152Rating / score1,371.64Votes180ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryrussianRank153Rating / score1,348.07Votes201ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryenglishRank154Rating / score1,359.58Votes1,388ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryexclude tiesRank155Rating / score1,293.06Votes2,264ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryhard promptsRank155Rating / score1,335.80Votes1,435ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryoverallRank155Rating / score1,338.43Votes3,321ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry software and it servicesRank156Rating / score1,359.54Votes1,179ObservationsN/AResult dateNov 11, 2026
ArenatextCategorynon englishRank156Rating / score1,315.63Votes1,933ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryenglishRank156Rating / score1,367.46Votes1,388ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryhard promptsRank156Rating / score1,363.90Votes1,435ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryexpertRank157Rating / score1,329.60Votes180ObservationsN/AResult dateNov 11, 2026
ArenatextCategorycodingRank158Rating / score1,355.99Votes652ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryhard prompts englishRank158Rating / score1,344.03Votes613ObservationsN/AResult dateNov 11, 2026

Llama 3.3 Nemotron Super 49B Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.40 input, $0.40 output per 1M via Deep Infra
Tracked offerings
1
1 row
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderDeep InfraProvider model IDnvidia/Llama-3.3-Nemotron-Super-49B-v1.5RegionglobalInput / 1M$0.40Output / 1M$0.40Context131.1KUpdatedNov 18, 2026

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

Llama 3.3 Nemotron Super 49B Runtime Performance

Provider-specific output speed and catalog latency for Llama 3.3 Nemotron Super 49B v1.5. 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.

Llama 3.3 Nemotron Super 49B Specifications

Technical details for the model's default version.

Version
Llama 3.3 Nemotron Super 49B v1.5
Released
Jul 25, 2025
Knowledge cutoff
Unknown
Parameters
N/A
Context window
131.1K
Max output
131.1K
Inputs
text
Outputs
text
Open weights
Yes
License
Unspecified

Llama 3.3 Nemotron Super 49B Versions

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

2 rows
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionLlama 3.3 Nemotron Super 49B v1.5ReleasedJul 25, 2025LLMBoardN/AParametersN/AContext131.1KMax output131.1KOpen weightsYesLicenseUnspecified
VersionLlama-3.3 Nemotron Super 49B v1ReleasedMar 18, 2025LLMBoard20.02Parameters49.9BContextN/AMax outputN/AOpen weightsYesLicenseLlama 3.1 Community License

Models similar to Llama 3.3 Nemotron Super 49B

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

#241+7.93
NV

Llama 3.1 Nemotron Ultra 253B

NVIDIA

27.95 LLMBoard

Details
#234+10.15
NV

Nemotron Nano 9B

NVIDIA

30.17 LLMBoard

Details
#227+12.57
NV

Nemotron 3 Nano

NVIDIA

32.59 LLMBoard

Details
#308-12.89
NV

Llama 3.1 Nemotron Nano 8B

NVIDIA

7.13 LLMBoard

Details
#209+16.06
NV

Nemotron 3.5 Lightning

NVIDIA

36.08 LLMBoard

Details
#206+16.68
NV

Nemotron Labs Dory 1.0

NVIDIA

36.70 LLMBoard

Details

What is Llama 3.3 Nemotron Super 49B?

Key information about Llama 3.3 Nemotron Super 49B and its available data.

3 Nemotron Super 49B is an NVIDIA Nemotron large language model (LLM) designed for reasoning, coding, and specialized AI agents.

Data as of 2026-11-17.

FAQ

Common questions about Llama 3.3 Nemotron Super 49B.

When was Llama 3.3 Nemotron Super 49B released?

Llama 3.3 Nemotron Super 49B's default version was released on Jul 25, 2025.

How much does Llama 3.3 Nemotron Super 49B cost?

No official standard PAYG price is currently available for Llama 3.3 Nemotron Super 49B. The lowest tracked third-party offer starts at $0.40 input and $0.40 output via Deep Infra.

Who created Llama 3.3 Nemotron Super 49B?

Llama 3.3 Nemotron Super 49B was created by NVIDIA.

What is the context window for Llama 3.3 Nemotron Super 49B?

The default version has a 131.1K token context window.

Is Llama 3.3 Nemotron Super 49B open weight?

Yes. The default version is marked as open weight under an unspecified license.

How many API providers offer Llama 3.3 Nemotron Super 49B?

1 provider offerings are linked to the default version.

Browse runtime rankings