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 Pro

Amazon Nova Pro is a highly-capable multimodal model with state-of-the-art performance across text, image, and video understanding.

Updated Aug 17, 2026. Default version: Nova Pro

Compare
LLMBoard Score20.3Nova Pro
Coverage100%24 benchmark families
Context window300KTokens
Official input price$0.80Amazon Bedrock API

On this page

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

Nova Pro Capability Profile

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

Nova Pro LLMBoard score breakdown

Nova Pro Benchmark Results

Benchmark scores for Nova Pro.

27 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkCRAGScore50.3%Rank01Participants3Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkFinQAScore77.2%Rank01Participants3Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkGroundUI-1KScore81.4%Rank01Participants2Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMM-Mind2WebScore63.7%Rank01Participants3Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTranslation en→Set1 COMET22Score89.1%Rank01Participants3Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTranslation en→Set1 spBleuScore43.4%Rank01Participants3Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTranslation Set1→en COMET22Score89.0%Rank01Participants3Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkTranslation Set1→en spBleuScore44.4%Rank01Participants3Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkVisualWebBenchScore79.7%Rank01Participants2Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkVATEXScore77.8%Rank02Participants2Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkBBHScore86.9%Rank03Participants12Percentile81.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkSQuALITYScore19.8%Rank03Participants5Percentile50.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkChartQAScore89.2%Rank04Participants26Percentile88.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkEgoSchemaScore72.1%Rank04Participants9Percentile62.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkARC-CScore94.8%Rank05Participants34Percentile87.9%EvidenceCEvaluatedAug 17, 2026
BenchmarkDROPScore85.4%Rank06Participants30Percentile82.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkTextVQAScore81.5%Rank07Participants16Percentile60.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkBFCLScore68.4%Rank08Participants11Percentile30.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkDocVQAScore93.5%Rank10Participants28Percentile66.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkIFEvalScore92.1%Rank10Participants67Percentile86.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkGSM8kScore94.8%Rank13Participants48Percentile74.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkHumanEvalScore89.0%Rank18Participants66Percentile73.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkLVBenchScore41.6%Rank24Participants25Percentile4.2%EvidenceCEvaluatedAug 17, 2026
BenchmarkMATHScore76.6%Rank25Participants71Percentile65.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMLUScore85.9%Rank36Participants101Percentile65.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMMUScore61.7%Rank43Participants63Percentile32.3%EvidenceCEvaluatedAug 17, 2026
BenchmarkGPQAScore46.9%Rank191Participants239Percentile20.2%EvidenceCEvaluatedAug 17, 2026

Nova Pro Arena Results

Preference and agent-evaluation results for the default version.

21 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenatextCategoryoverallRank42Rating / score1447.3Votes3,409ObservationsN/AResult dateAug 12, 2026
Arenatext factualityCategoryoverallRank53Rating / score1450.0Votes3,409ObservationsN/AResult dateAug 12, 2026
ArenatextCategoryoverallRank96Rating / score1420.1Votes3,708ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank99Rating / score1425.7Votes3,409ObservationsN/AResult dateAug 12, 2026
Arenatext factualityCategoryoverallRank103Rating / score1424.1Votes3,525ObservationsN/AResult dateAug 12, 2026
ArenatextCategoryoverallRank111Rating / score1416.1Votes25,448ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank118Rating / score1415.2Votes3,422ObservationsN/AResult dateAug 12, 2026
Arenatext factualityCategoryoverallRank119Rating / score1415.3Votes24,962ObservationsN/AResult dateAug 12, 2026
Arenatext factualityCategoryoverallRank128Rating / score1404.6Votes3,422ObservationsN/AResult dateAug 12, 2026
Arenavision style controlCategoryoverallRank130Rating / score1019.5Votes2,335ObservationsN/AResult dateAug 6, 2026
Arenatext factualityCategoryoverallRank132Rating / score1400.1Votes11,112ObservationsN/AResult dateAug 12, 2026
ArenatextCategoryoverallRank133Rating / score1398.3Votes3,422ObservationsN/AResult dateAug 12, 2026
ArenavisionCategoryoverallRank133Rating / score980.6Votes2,335ObservationsN/AResult dateAug 6, 2026
ArenatextCategoryoverallRank138Rating / score1394.7Votes11,536ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank148Rating / score1393.9Votes3,708ObservationsN/AResult dateAug 12, 2026
ArenatextCategoryoverallRank168Rating / score1364.5Votes2,836ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank178Rating / score1365.7Votes25,448ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank194Rating / score1349.6Votes11,536ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank199Rating / score1347.4Votes2,836ObservationsN/AResult dateAug 12, 2026
ArenatextCategoryoverallRank264Rating / score1258.8Votes24,745ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank265Rating / score1290.1Votes24,745ObservationsN/AResult dateAug 12, 2026

Nova Pro Pricing

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

Official API
$0.80 input, $3.2 output per 1M
Official provider
Amazon Bedrock
Lowest third-party
From $0.80 input, $3.2 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-pro-v1:0RegionglobalInput / 1M$0.80Output / 1M$3.2Context300KUpdatedAug 17, 2026
ProviderVercel AI GatewayProvider model IDamazon/nova-proRegionglobalInput / 1M$0.80Output / 1M$3.2Context300KUpdatedAug 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 Pro Runtime Performance

Provider-specific output speed and catalog latency for Nova Pro. 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 Output300KUpdatedAug 17, 2026

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

Nova Pro Specifications

Technical details for the model's default version.

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

Nova Pro 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 ProReleasedNov 20, 2024LLMBoard20.3ParametersN/AContext300KMax output300KOpen weightsNoLicenseProprietary

Nova Pro vs nearby models

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

Nova ProvsPixtral LargeNova ProvsGemini 2.0 Flash LiteNova ProvsGrok 2Nova ProvsMin istral 3Nova ProvsGemini 1.5 ProNova ProvsMagistral Small

Models similar to Nova Pro

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

#210-4.2
AM

Nova 2 Sonic

Amazon

16.1 LLMBoard

DetailsCompare
#224-7.6
AM

Nova Lite

Amazon

12.7 LLMBoard

DetailsCompare
#248-16.5
AM

Nova Micro

Amazon

3.8 LLMBoard

DetailsCompare
#127+22.1
AM

Nova 2 Lite

Amazon

42.4 LLMBoard

DetailsCompare
#123+23.1
AM

Nova 2 Omni

Amazon

43.4 LLMBoard

DetailsCompare
#93+31.7
AM

Nova 2 Pro

Amazon

52.0 LLMBoard

DetailsCompare

What is Nova Pro?

Key information about Nova Pro and its available data.

Amazon Nova Pro is a highly-capable multimodal model with state-of-the-art performance across text, image, and video understanding. It excels at core capabilities like language understanding, mathematical reasoning, and multimodal tasks while offering industry-leading speed and cost efficiency.

Data as of 2026-08-17.

FAQ

Common questions about Nova Pro.

When was Nova Pro released?

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

How much does Nova Pro cost?

Nova Pro's official API price is $0.80 per million input tokens and $3.2 per million output tokens via Amazon Bedrock. The lowest tracked third-party offer starts at $0.80 input and $3.2 output via Vercel AI Gateway.

Who created Nova Pro?

Nova Pro was created by Amazon.

What is the context window for Nova Pro?

The default version has a 300K token context window.

Is Nova Pro open weight?

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

How many API providers offer Nova Pro?

2 provider offerings are linked to the default version.

What models should I compare Nova Pro with?

Nearby ranked alternatives include Pixtral Large, Gemini 2.0 Flash Lite, Grok 2.