llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsNova 2 Lite

Amazon model product

Nova 2 Lite

Amazon Nova 2 Lite is a low-latency, cost-effective multimodal reasoning model for everyday workloads. It processes text, images, and video to generate text output, with hybrid reasoning controls that let developers toggle extended thinking on or off and adjust depth (low, medium, high) to balance accuracy, speed, and cost. It supports up to 1M tokens of context and matches or exceeds Claude Haiku 4.5, GPT-5 Mini, and Gemini 2.5 Flash on most standard benchmarks.

Updated Aug 10, 2026. Default version: Nova 2 Lite

Compare
LLMBoard score55.1Nova 2 Lite
Coverage60%7 benchmark families
Context window1MTokens
Official input price$0.33Amazon Bedrock API

On this page

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

Model specification

Structured fields from the published default version.

Version
Nova 2 Lite
Released
Dec 2, 2025
Knowledge cutoff
Unknown
Parameters
N/A
Context window
1M
Max output
65.5K
Inputs
image, text, video
Outputs
text
Open weights
No
License
Proprietary

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Nova 2 Lite category scores

Benchmark results

Published benchmark records for the scored version Nova 2 Lite.

19 rows
Columns

Show columns

LongCodeBench0.812100.0%CAug 7, 2026
QVHighlights0.813100.0%CAug 7, 2026
Multi-Challenge0.822996.4%CAug 7, 2026
RealKIE-FCC0.62350.0%CAug 7, 2026
OCRBench_V20.6770.0%CAug 7, 2026
Tau2 Airline0.682368.2%CAug 7, 2026
BFCL-V40.691333.3%CAug 7, 2026
Tau2 Retail0.8142648.0%CAug 7, 2026
IFBench0.7152848.1%CAug 7, 2026
ScreenSpot0.816160.0%CAug 7, 2026
Terminal-Bench0.3172533.3%CAug 7, 2026
LiveCodeBench0.7207373.6%CAug 7, 2026
Tau2 Telecom0.8233535.3%CAug 7, 2026
MCP Atlas0.230300.0%CAug 7, 2026
AIME 20250.94411462.0%CAug 7, 2026
MMMU-Pro0.6456531.3%CAug 7, 2026
MMLU-Pro0.84812963.3%CAug 7, 2026
SWE-Bench Verified0.67310430.1%CAug 7, 2026
GPQA0.88923362.1%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

73 rows
Columns

Show columns

text factualityrussian1041372.9668N/AAug 6, 2026
text factualityindustry life and physical and social science1151407.61,216N/AAug 6, 2026
text factualitycreative writing1211316.3978N/AAug 6, 2026
text factualityindustry business and management and financial operations1211387.21,439N/AAug 6, 2026
text factualityindustry entertainment and sports and media1231327.61,317N/AAug 6, 2026
text factualitycoding1241427.61,528N/AAug 6, 2026
text factualitymulti turn1241360.51,257N/AAug 6, 2026
text factualityindustry writing and literature and language1251352.01,718N/AAug 6, 2026
text factualityinstruction following1281370.92,163N/AAug 6, 2026
text factualityhard prompts english1301407.72,057N/AAug 6, 2026
text factualitylonger query1311368.71,853N/AAug 6, 2026
text factualityindustry software and it services1341415.22,969N/AAug 6, 2026
text factualityenglish1361399.95,477N/AAug 6, 2026
text factualityhard prompts1371398.16,162N/AAug 6, 2026
text factualityexclude ties1381356.48,370N/AAug 6, 2026
text factualitynon english1381358.46,140N/AAug 6, 2026
text factualityoverall1391381.011,749N/AAug 6, 2026
textfrench1441376.7224N/AAug 6, 2026
textgerman1441354.5263N/AAug 6, 2026
textindustry business and management and financial operations1481368.22,280N/AAug 6, 2026
textspanish1481361.4201N/AAug 6, 2026
textindustry medicine and healthcare1511386.5707N/AAug 6, 2026
textindustry software and it services1511394.14,242N/AAug 6, 2026
textexpert1521367.1712N/AAug 6, 2026
textenglish1551383.45,744N/AAug 6, 2026
textindustry life and physical and social science1561381.62,059N/AAug 6, 2026
textcoding1571388.02,507N/AAug 6, 2026
texthard prompts english1581381.13,195N/AAug 6, 2026
textindustry mathematical1631370.6582N/AAug 6, 2026
textpolish1631324.5411N/AAug 6, 2026
texthard prompts1641365.16,468N/AAug 6, 2026
textkorean1641272.7148N/AAug 6, 2026
textrussian1671339.61,169N/AAug 6, 2026
textexclude ties1681327.18,750N/AAug 6, 2026
textoverall1691362.812,213N/AAug 6, 2026
textnon english1701338.86,412N/AAug 6, 2026
textinstruction following1721335.13,322N/AAug 6, 2026
textindustry legal and government1731355.2887N/AAug 6, 2026
textchinese1741368.4682N/AAug 6, 2026
textmath1761360.2825N/AAug 6, 2026
text style controlgerman1791315.1263N/AAug 6, 2026
textlonger query1801336.22,907N/AAug 6, 2026
text style controlexpert1811361.6712N/AAug 6, 2026
textindustry entertainment and sports and media1821306.92,205N/AAug 6, 2026
text style controlfrench1831345.7224N/AAug 6, 2026
text style controlspanish1831330.7201N/AAug 6, 2026
textindustry writing and literature and language1861318.82,743N/AAug 6, 2026
text style controlindustry business and management and financial operations1861351.02,280N/AAug 6, 2026
textmulti turn1871337.92,068N/AAug 6, 2026
text style controlcoding1881395.52,507N/AAug 6, 2026
text style controlindustry software and it services1911385.54,242N/AAug 6, 2026
text style controlhard prompts english1931377.53,195N/AAug 6, 2026
text style controlindustry mathematical1931349.1582N/AAug 6, 2026
text style controlindustry medicine and healthcare1941360.0707N/AAug 6, 2026
text style controlpolish1971283.0411N/AAug 6, 2026
textcreative writing1981294.41,716N/AAug 6, 2026
text style controlinstruction following1981329.33,322N/AAug 6, 2026
text style controlmath1981333.4825N/AAug 6, 2026
text style controlenglish2001361.75,744N/AAug 6, 2026
text style controlhard prompts2001358.76,468N/AAug 6, 2026
text style controlindustry life and physical and social science2041356.52,059N/AAug 6, 2026
text style controlexclude ties2071291.98,750N/AAug 6, 2026
text style controlkorean2071231.5148N/AAug 6, 2026
text style controloverall2091336.612,213N/AAug 6, 2026
text style controlrussian2101317.41,169N/AAug 6, 2026
text style controlchinese2111342.4682N/AAug 6, 2026
text style controllonger query2151335.52,907N/AAug 6, 2026
text style controlmulti turn2161323.82,068N/AAug 6, 2026
text style controlnon english2161308.26,412N/AAug 6, 2026
text style controlindustry legal and government2261331.3887N/AAug 6, 2026
text style controlindustry entertainment and sports and media2311282.52,205N/AAug 6, 2026
text style controlindustry writing and literature and language2331300.72,743N/AAug 6, 2026
text style controlcreative writing2461273.81,716N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$0.33 input, $2.75 output per 1M
Official provider
Amazon Bedrock
Lowest third-party
From $0.30 input, $2.5 output per 1M via Vercel AI Gateway
Tracked offerings
5
5 rows
Columns

Show columns

Novanova-2-lite-v1globalN/AN/A1MAug 7, 2026
Vercel AI Gatewayamazon/nova-2-liteglobal$0.30$2.51MAug 7, 2026
OpenRouteramazon/nova-2-lite-v1global$0.30$2.51MAug 7, 2026
Amazon Bedrockamazon.nova-2-lite-v1:0global$0.33$2.75128KAug 7, 2026
Cortecsnova-2-liteglobal$0.373$3.141MAug 7, 2026

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

Nova 2 Lite versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Nova 2 LiteDec 2, 202555.1N/A1M65.5KNoProprietary

What is Nova 2 Lite?

A concise description based on the published model registry.

Amazon Nova 2 Lite is a low-latency, cost-effective multimodal reasoning model for everyday workloads. It processes text, images, and video to generate text output, with hybrid reasoning controls that let developers toggle extended thinking on or off and adjust depth (low, medium, high) to balance accuracy, speed, and cost. It supports up to 1M tokens of context and matches or exceeds Claude Haiku 4.5, GPT-5 Mini, and Gemini 2.5 Flash on most standard benchmarks.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Nova 2 Lite vs nearby models

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

Nova 2 LitevsMiMo V2 FlashNova 2 Litevso3Nova 2 LitevsGLM 4.5 AirNova 2 Litevso4 miniNova 2 LitevsMiniMax M2.1Nova 2 LitevsLlama 3.3 70B

Models similar to Nova 2 Lite

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

#84-5.9
AM

Nova Lite

Amazon

49.2 LLMBoard

DetailsCompare
#43+8.4
AM

Nova Pro

Amazon

63.5 LLMBoard

DetailsCompare
#123-18.8
AM

Nova Micro

Amazon

36.3 LLMBoard

DetailsCompare
#20+20.0
AM

Nova 2 Pro

Amazon

75.1 LLMBoard

DetailsCompare
#65+0.1
ZA

GLM 4.5 Air

Zhipu AI

55.1 LLMBoard

DetailsCompare
#67-0.1
OP

o4 mini

OpenAI

55.0 LLMBoard

DetailsCompare

FAQ

Common questions about Nova 2 Lite.

When was Nova 2 Lite released?

Nova 2 Lite's default version was released on Dec 2, 2025.

How much does Nova 2 Lite cost?

Nova 2 Lite's official API price is $0.33 per million input tokens and $2.75 per million output tokens via Amazon Bedrock. The lowest tracked third-party offer starts at $0.30 input and $2.5 output via Vercel AI Gateway.

Who created Nova 2 Lite?

Nova 2 Lite is published under Amazon in the model registry.

What is the context window for Nova 2 Lite?

The default version has a 1M token context window.

Is Nova 2 Lite open weight?

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

How many API providers offer Nova 2 Lite?

5 published provider offerings are linked to the default version.

What models should I compare Nova 2 Lite with?

Nearby ranked alternatives include MiMo V2 Flash, o3, GLM 4.5 Air.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai