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
1367 models808 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 3.5 Super VL

5 Super VL is an open multimodal Mixture-of-Experts model that accepts text, image, and video inputs and produces text.

Updated Oct 23, 2026. Default version: Nemotron 3.5 Super VL (120B A12B)

LLMBoard Score57.1Nemotron 3.5 Super VL (120B A12B)
Coverage20%19 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 3.5 Super VL Capability Profile

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

Nemotron 3.5 Super VL (120B A12B) LLMBoard score breakdown

Nemotron 3.5 Super VL Benchmark Results

Benchmark scores for Nemotron 3.5 Super VL (120B A12B).

25 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkMMLongBench-DocScore0.63 pointsRank01Participants7Percentile100.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkOCRBench-V2 (en)Score68.12%Rank02Participants15Percentile92.86%EvidenceCEvaluatedOct 22, 2026
BenchmarkOmniScienceScore26.20%Rank04Participants7Percentile50.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkLiveCodeBench v6Score88.22%Rank09Participants67Percentile87.88%EvidenceCEvaluatedOct 22, 2026
BenchmarkTau3 BankingScore18.88%Rank10Participants16Percentile40.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkAA-LCRScore68.62%Rank12Participants27Percentile57.69%EvidenceCEvaluatedOct 22, 2026
BenchmarkSciCodeScore47.13%Rank13Participants31Percentile60.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkGDPval-AAScore1,211.00 pointsRank14Participants17Percentile18.75%EvidenceCEvaluatedOct 22, 2026
BenchmarkMathVisionScore78.16%Rank18Participants38Percentile54.05%EvidenceCEvaluatedOct 22, 2026
BenchmarkBrowseCompScore78.00%Rank24Participants70Percentile66.67%EvidenceCEvaluatedOct 22, 2026
BenchmarkCharXiv-RScore80.82%Rank27Participants60Percentile55.93%EvidenceCEvaluatedOct 22, 2026
BenchmarkOSWorld-VerifiedScore51.14%Rank27Participants28Percentile3.70%EvidenceCEvaluatedOct 22, 2026
BenchmarkIFBenchScore70.86%Rank30Participants46Percentile35.56%EvidenceCEvaluatedOct 22, 2026
BenchmarkSWE-bench MultilingualScore67.72%Rank31Participants50Percentile38.78%EvidenceCEvaluatedOct 22, 2026
BenchmarkGPQAScore89.52%Rank32Participants256Percentile87.84%EvidenceCEvaluatedOct 22, 2026
BenchmarkTerminal-Bench 2.1Score66.70%Rank33Participants48Percentile31.91%EvidenceCEvaluatedOct 22, 2026
BenchmarkHumanity's Last ExamScore31.79%Rank53Participants109Percentile51.85%EvidenceCEvaluatedOct 22, 2026
BenchmarkSWE-Bench ProScore51.78%Rank55Participants63Percentile12.90%EvidenceCEvaluatedOct 22, 2026
BenchmarkSWE-Bench VerifiedScore71.10%Rank64Participants120Percentile47.06%EvidenceCEvaluatedOct 22, 2026
BenchmarkLM Arena WebdevScore1,403.82 ratingRank68Participants107Percentile36.79%EvidenceAEvaluatedOct 19, 2026
BenchmarkLM Arena Vision Style ControlScore1,204.01 ratingRank72Participants113Percentile36.61%EvidenceAEvaluatedOct 19, 2026
BenchmarkLM Arena VisionScore1,204.75 ratingRank73Participants113Percentile35.71%EvidenceAEvaluatedOct 19, 2026
BenchmarkLM Arena Text FactualityScore1,425.30 ratingRank93Participants131Percentile29.23%EvidenceAEvaluatedOct 20, 2026
BenchmarkLM Arena Text Style ControlScore1,414.22 ratingRank106Participants218Percentile51.61%EvidenceAEvaluatedOct 20, 2026
BenchmarkLM Arena TextScore1,406.64 ratingRank108Participants218Percentile50.69%EvidenceAEvaluatedOct 20, 2026

Nemotron 3.5 Super VL Arena Results

Preference and agent-evaluation results for the default version.

30 of 80 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
Arenavision style controlCategorycreative writing visionRank43Rating / score1,236.52Votes193ObservationsN/AResult dateOct 19, 2026
ArenawebdevCategoryimage to webdevRank44Rating / score1,406.77Votes991ObservationsN/AResult dateOct 19, 2026
ArenavisionCategorycreative writing visionRank54Rating / score1,231.25Votes193ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryenglishRank55Rating / score1,236.85Votes864ObservationsN/AResult dateOct 19, 2026
Arenatext factualityCategoryindustry business and management and financial operationsRank59Rating / score1,449.06Votes607ObservationsN/AResult dateOct 20, 2026
ArenavisionCategoryenglishRank62Rating / score1,238.71Votes864ObservationsN/AResult dateOct 19, 2026
ArenawebdevCategorywebdev-reactRank64Rating / score1,399.13Votes1,220ObservationsN/AResult dateOct 19, 2026
Arenatext factualityCategoryindustry life and physical and social scienceRank65Rating / score1,462.67Votes645ObservationsN/AResult dateOct 20, 2026
ArenawebdevCategorywebdev-htmlRank66Rating / score1,415.72Votes211ObservationsN/AResult dateOct 19, 2026
ArenawebdevCategoryoverallRank68Rating / score1,403.82Votes1,843ObservationsN/AResult dateOct 19, 2026
ArenawebdevCategorywebdevRank68Rating / score1,403.82Votes1,843ObservationsN/AResult dateOct 19, 2026
ArenavisionCategorydiagramRank69Rating / score1,223.34Votes651ObservationsN/AResult dateOct 19, 2026
ArenavisionCategoryhomeworkRank69Rating / score1,229.12Votes380ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryocrRank69Rating / score1,219.65Votes1,672ObservationsN/AResult dateOct 19, 2026
ArenavisionCategoryocrRank70Rating / score1,215.61Votes1,672ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategorydiagramRank70Rating / score1,230.39Votes651ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryhomeworkRank71Rating / score1,233.27Votes380ObservationsN/AResult dateOct 19, 2026
Arenatext factualityCategorymulti turnRank72Rating / score1,446.15Votes590ObservationsN/AResult dateOct 20, 2026
Arenavision style controlCategoryoverallRank72Rating / score1,204.01Votes2,509ObservationsN/AResult dateOct 19, 2026
ArenavisionCategoryoverallRank73Rating / score1,204.75Votes2,509ObservationsN/AResult dateOct 19, 2026
Arenatext factualityCategoryrussianRank74Rating / score1,432.31Votes493ObservationsN/AResult dateOct 20, 2026
ArenatextCategoryexpertRank82Rating / score1,437.20Votes437ObservationsN/AResult dateOct 20, 2026
Arenatext factualityCategorycreative writingRank82Rating / score1,400.92Votes899ObservationsN/AResult dateOct 20, 2026
Arenatext factualityCategoryenglishRank84Rating / score1,444.17Votes1,543ObservationsN/AResult dateOct 20, 2026
Arenatext factualityCategoryhard prompts englishRank84Rating / score1,464.25Votes976ObservationsN/AResult dateOct 20, 2026
Arenatext factualityCategoryinstruction followingRank84Rating / score1,424.09Votes1,376ObservationsN/AResult dateOct 20, 2026
Arenatext factualityCategoryindustry software and it servicesRank86Rating / score1,469.26Votes1,426ObservationsN/AResult dateOct 20, 2026
ArenatextCategorychineseRank87Rating / score1,457.99Votes277ObservationsN/AResult dateOct 20, 2026
ArenatextCategoryindustry software and it servicesRank88Rating / score1,442.26Votes1,426ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryexpertRank88Rating / score1,450.83Votes437ObservationsN/AResult dateOct 20, 2026

Nemotron 3.5 Super VL Pricing

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

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.08 input, $0.45 output per 1M via Pioneer
Tracked offerings
6
6 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderNvidiaProvider model IDnvidia/nemotron-3.5-super-vl-120b-a12bRegionglobalInput / 1MN/AOutput / 1MN/AContext1MUpdatedOct 23, 2026
ProviderPioneerProvider model IDnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4RegionglobalInput / 1M$0.08Output / 1M$0.45Context262.1KUpdatedOct 23, 2026
ProviderTogether AIProvider model IDnvidia/NVIDIA-Nemotron-3.5-Super-VLRegionglobalInput / 1M$0.15Output / 1M$0.50Context262.1KUpdatedOct 23, 2026
ProviderNebius Token FactoryProvider model IDnvidia/Nemotron-3.5-Super-VLRegionglobalInput / 1M$0.30Output / 1M$0.90Context1MUpdatedOct 23, 2026
ProviderThinking MachinesProvider model IDnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16RegionglobalInput / 1M$0.57Output / 1M$1.44Context65.5KUpdatedOct 23, 2026
ProviderThinking MachinesProvider model IDnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:peft:262144RegionglobalInput / 1M$0.57Output / 1M$1.44Context262.1KUpdatedOct 23, 2026

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

Nemotron 3.5 Super VL Runtime Performance

Provider-specific output speed and catalog latency for Nemotron 3.5 Super VL (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 3.5 Super VL Specifications

Technical details for the model's default version.

Version
Nemotron 3.5 Super VL (120B A12B)
Released
Oct 15, 2026
Knowledge cutoff
Unknown
Parameters
120B
Context window
262.1K
Max output
262.1K
Inputs
image, text, video
Outputs
text
Open weights
Yes
License
OpenMDW License v1.1

Nemotron 3.5 Super VL 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 3.5 Super VL (120B A12B)ReleasedOct 15, 2026LLMBoard57.09Parameters120BContext262.1KMax output262.1KOpen weightsYesLicenseOpenMDW License v1.1

Models similar to Nemotron 3.5 Super VL

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

#89+3.66
NV

Nemotron 3 Ultra

NVIDIA

60.75 LLMBoard

Details
#136-7.45
NV

Nemotron 3.5 Bolt

NVIDIA

49.64 LLMBoard

Details
#158-13.84
NV

Nemotron 3 Super

NVIDIA

43.25 LLMBoard

Details
#184-20.04
NV

Nemotron Labs Dory 1.0

NVIDIA

37.05 LLMBoard

Details
#185-20.20
NV

Nemotron 3.5 Lightning

NVIDIA

36.89 LLMBoard

Details
#203-24.12
NV

Nemotron 3 Nano

NVIDIA

32.97 LLMBoard

Details

What is Nemotron 3.5 Super VL?

Key information about Nemotron 3.5 Super VL and its available data.

5 Super VL is an open multimodal 120B total / 12B active Mixture-of-Experts model with a hybrid Mamba-2 + Attention architecture and a C-RADIO / RADIO vision encoder. 1.

Data as of 2026-10-22.

FAQ

Common questions about Nemotron 3.5 Super VL.

When was Nemotron 3.5 Super VL released?

Nemotron 3.5 Super VL's default version was released on Oct 15, 2026.

How much does Nemotron 3.5 Super VL cost?

No official standard PAYG price is currently available for Nemotron 3.5 Super VL. The lowest tracked third-party offer starts at $0.08 input and $0.45 output via Pioneer.

Who created Nemotron 3.5 Super VL?

Nemotron 3.5 Super VL was created by NVIDIA.

What is the context window for Nemotron 3.5 Super VL?

The default version has a 262.1K token context window.

Is Nemotron 3.5 Super VL open weight?

Yes. The default version is marked as open weight under OpenMDW License v1.1.

How many API providers offer Nemotron 3.5 Super VL?

6 provider offerings are linked to the default version.

Browse runtime rankings