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 DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 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 BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

NVIDIA model product

Nemotron 3.5 Lightning

5 Lightning is an open 30B mixture-of-experts (MoE) model with ~3B active parameters, built for high-throughput specialized task execution in long-running / always-on agents.

Updated Aug 17, 2026. Default version: Nemotron 3.5 Lightning (30B A3B)

Compare
LLMBoard Score37.3Nemotron 3.5 Lightning (30B A3B)
Coverage80%13 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable

On this page

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

Nemotron 3.5 Lightning Capability Profile

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

Nemotron 3.5 Lightning (30B A3B) LLMBoard score breakdown

Nemotron 3.5 Lightning Benchmark Results

Benchmark scores for Nemotron 3.5 Lightning (30B A3B).

13 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkPinchBenchScore85.4%Rank02Participants6Percentile80.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkOmniScienceScore17.5%Rank03Participants3Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTau3 BankingScore9.3%Rank06Participants7Percentile16.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkAA-LCRScore52.0%Rank16Participants18Percentile11.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkIFBenchScore71.9%Rank17Participants34Percentile51.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkSciCodeScore32.6%Rank21Participants21Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTerminal-Bench 2.1Score24.6%Rank28Participants28Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkSWE-bench MultilingualScore39.3%Rank36Participants38Percentile5.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMLU-ProScore81.9%Rank43Participants134Percentile68.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkBrowseCompScore37.0%Rank56Participants62Percentile9.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkHumanity's Last ExamScore11.7%Rank84Participants99Percentile15.3%EvidenceCEvaluatedAug 17, 2026
BenchmarkSWE-Bench VerifiedScore51.6%Rank94Participants111Percentile15.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkGPQAScore75.4%Rank107Participants239Percentile55.5%EvidenceCEvaluatedAug 17, 2026

Nemotron 3.5 Lightning Arena Results

Preference and agent-evaluation results for the default version.

No Arena results

The default version does not have a matching Arena result yet.

Nemotron 3.5 Lightning Pricing

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

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No provider prices

The default version has no current input or output token prices.

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 Lightning Runtime Performance

Provider-specific output speed and catalog latency for Nemotron 3.5 Lightning (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.

Browse runtime rankings

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Nemotron 3.5 Lightning Specifications

Technical details for the model's default version.

Version
Nemotron 3.5 Lightning (30B A3B)
Released
Aug 11, 2026
Knowledge cutoff
Unknown
Parameters
30B
Context window
262.1K
Max output
262.1K
Inputs
text
Outputs
text
Open weights
Yes
License
OpenMDW License v1.1

Nemotron 3.5 Lightning Versions

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

1 rows
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionNemotron 3.5 Lightning (30B A3B)ReleasedAug 11, 2026LLMBoard37.3Parameters30BContext262.1KMax output262.1KOpen weightsYesLicenseOpenMDW License v1.1

Nemotron 3.5 Lightning vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Nemotron 3.5 LightningvsGLM 4.7 FlashNemotron 3.5 LightningvsClaude Sonnet 3.7Nemotron 3.5 LightningvsGemma 4 12BNemotron 3.5 LightningvsKimi K2Nemotron 3.5 LightningvsNorth Mini Code 1.0Nemotron 3.5 LightningvsMiniMax M1 80K

Models similar to Nemotron 3.5 Lightning

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

#156-2.4
NV

Nemotron 3 Nano

NVIDIA

34.9 LLMBoard

DetailsCompare
#166-5.6
NV

Nemotron Nano 9B

NVIDIA

31.7 LLMBoard

DetailsCompare
#119+7.0
NV

Nemotron 3 Super

NVIDIA

44.3 LLMBoard

DetailsCompare
#172-7.3
NV

Llama 3.1 Nemotron Ultra 253B

NVIDIA

30.0 LLMBoard

DetailsCompare
#192-15.0
NV

Llama 3.3 Nemotron Super 49B

NVIDIA

22.3 LLMBoard

DetailsCompare
#57+25.4
NV

Nemotron 3 Ultra

NVIDIA

62.7 LLMBoard

DetailsCompare

What is Nemotron 3.5 Lightning?

Key information about Nemotron 3.5 Lightning and its available data.

5 Lightning is an open 30B mixture-of-experts (MoE) model with ~3B active parameters, built for high-throughput specialized task execution in long-running / always-on agents.

It ships with speculative decoding (MTP, DFlash, DSpark), NVFP4 and BF16 checkpoints, and is designed to pair with NVIDIA NeMo Switchyard for routing execution work alongside frontier planners. 1.

Data as of 2026-08-17.

FAQ

Common questions about Nemotron 3.5 Lightning.

When was Nemotron 3.5 Lightning released?

Nemotron 3.5 Lightning's default version was released on Aug 11, 2026.

How much does Nemotron 3.5 Lightning cost?

No official standard PAYG price is currently available for Nemotron 3.5 Lightning.

Who created Nemotron 3.5 Lightning?

Nemotron 3.5 Lightning was created by NVIDIA.

What is the context window for Nemotron 3.5 Lightning?

The default version has a 262.1K token context window.

Is Nemotron 3.5 Lightning open weight?

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

How many API providers offer Nemotron 3.5 Lightning?

No provider offering is currently linked to the default version.

What models should I compare Nemotron 3.5 Lightning with?

Nearby ranked alternatives include GLM 4.7 Flash, Claude Sonnet 3.7, Gemma 4 12B.