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

Amazon model product

Nova Lite

A low-cost multimodal model that is lightning fast for processing images, video, documents, and text.

Updated Aug 17, 2026. Default version: Nova Lite

Compare
LLMBoard Score12.7Nova Lite
Coverage100%24 benchmark families
Context window300KTokens
Official input price$0.06Amazon Bedrock API

On this page

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

Nova Lite Capability Profile

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

Nova Lite LLMBoard score breakdown

Nova Lite Benchmark Results

Benchmark scores for Nova Lite.

27 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkVATEXScore77.8%Rank01Participants2Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkCRAGScore43.8%Rank02Participants3Percentile50.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkFinQAScore73.6%Rank02Participants3Percentile50.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkGroundUI-1KScore80.2%Rank02Participants2Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMM-Mind2WebScore60.7%Rank02Participants3Percentile50.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTranslation en→Set1 COMET22Score88.8%Rank02Participants3Percentile50.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTranslation en→Set1 spBleuScore41.5%Rank02Participants3Percentile50.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTranslation Set1→en COMET22Score88.8%Rank02Participants3Percentile50.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTranslation Set1→en spBleuScore43.1%Rank02Participants3Percentile50.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkVisualWebBenchScore77.7%Rank02Participants2Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkSQuALITYScore19.2%Rank04Participants5Percentile25.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkBBHScore82.4%Rank06Participants12Percentile54.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkEgoSchemaScore71.4%Rank06Participants9Percentile37.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkARC-CScore92.4%Rank08Participants34Percentile78.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkBFCLScore66.6%Rank09Participants11Percentile20.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTextVQAScore80.2%Rank09Participants16Percentile46.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkChartQAScore86.8%Rank10Participants26Percentile64.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkDROPScore80.2%Rank12Participants30Percentile62.1%EvidenceCEvaluatedAug 17, 2026
BenchmarkGSM8kScore94.5%Rank15Participants48Percentile70.2%EvidenceCEvaluatedAug 17, 2026
BenchmarkDocVQAScore92.4%Rank16Participants28Percentile44.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkIFEvalScore89.7%Rank19Participants67Percentile72.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkLVBenchScore40.4%Rank25Participants25Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMATHScore73.3%Rank31Participants71Percentile57.1%EvidenceCEvaluatedAug 17, 2026
BenchmarkHumanEvalScore85.4%Rank35Participants66Percentile47.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMMUScore56.2%Rank50Participants63Percentile21.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMLUScore80.5%Rank59Participants101Percentile42.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkGPQAScore42.0%Rank205Participants239Percentile14.3%EvidenceCEvaluatedAug 17, 2026

Nova Lite Arena Results

Preference and agent-evaluation results for the default version.

4 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenavisionCategoryoverallRank130Rating / score990.6Votes1,854ObservationsN/AResult dateAug 6, 2026
Arenavision style controlCategoryoverallRank131Rating / score1019.3Votes1,854ObservationsN/AResult dateAug 6, 2026
ArenatextCategoryoverallRank276Rating / score1228.6Votes19,372ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank291Rating / score1260.4Votes19,372ObservationsN/AResult dateAug 12, 2026

Nova Lite Pricing

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

Official API
$0.06 input, $0.24 output per 1M
Official provider
Amazon Bedrock
Lowest third-party
From $0.06 input, $0.24 output per 1M via Vercel AI Gateway
Tracked offerings
2
2 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderAmazon BedrockProvider model IDamazon.nova-lite-v1:0RegionglobalInput / 1M$0.06Output / 1M$0.24Context300KUpdatedAug 17, 2026
ProviderVercel AI GatewayProvider model IDamazon/nova-liteRegionglobalInput / 1M$0.06Output / 1M$0.24Context300KUpdatedAug 17, 2026

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

Nova Lite Runtime Performance

Provider-specific output speed and catalog latency for Nova Lite. Runtime does not affect the capability score.

1 rows
Columns

Show columns

Sort by
Provider
Output Speed
Catalog Latency
Max Input
Max Output
Updated
ProviderBedrockOutput Speed100 tok/sCatalog Latency0.5 sMax Input300KMax Output2KUpdatedAug 17, 2026

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

Nova Lite Specifications

Technical details for the model's default version.

Version
Nova Lite
Released
Nov 20, 2024
Knowledge cutoff
Unknown
Parameters
N/A
Context window
300K
Max output
2K
Inputs
image, text
Outputs
text
Open weights
No
License
Proprietary

Nova Lite 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
VersionNova LiteReleasedNov 20, 2024LLMBoard12.7ParametersN/AContext300KMax output2KOpen weightsNoLicenseProprietary

Nova Lite vs nearby models

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

Nova LitevsDeepSeek-V2.5Nova LitevsLlama 4 ScoutNova LitevsPhi 4 Mini ReasoningNova LitevsLlama 3.1 70BNova LitevsQwen2.5 VL 7BNova LitevsDeepSeek-R1-Distill-Llama

Models similar to Nova Lite

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

#210+3.4
AM

Nova 2 Sonic

Amazon

16.1 LLMBoard

DetailsCompare
#201+7.6
AM

Nova Pro

Amazon

20.3 LLMBoard

DetailsCompare
#248-8.9
AM

Nova Micro

Amazon

3.8 LLMBoard

DetailsCompare
#127+29.7
AM

Nova 2 Lite

Amazon

42.4 LLMBoard

DetailsCompare
#123+30.7
AM

Nova 2 Omni

Amazon

43.4 LLMBoard

DetailsCompare
#93+39.3
AM

Nova 2 Pro

Amazon

52.0 LLMBoard

DetailsCompare

What is Nova Lite?

Key information about Nova Lite and its available data.

A low-cost multimodal model that is lightning fast for processing images, video, documents, and text.

Data as of 2026-08-17.

FAQ

Common questions about Nova Lite.

When was Nova Lite released?

Nova Lite's default version was released on Nov 20, 2024.

How much does Nova Lite cost?

Nova Lite's official API price is $0.06 per million input tokens and $0.24 per million output tokens via Amazon Bedrock. The lowest tracked third-party offer starts at $0.06 input and $0.24 output via Vercel AI Gateway.

Who created Nova Lite?

Nova Lite was created by Amazon.

What is the context window for Nova Lite?

The default version has a 300K token context window.

Is Nova Lite open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Nova Lite?

2 provider offerings are linked to the default version.

What models should I compare Nova Lite with?

Nearby ranked alternatives include DeepSeek-V2.5, Llama 4 Scout, Phi 4 Mini Reasoning.