Nova Lite

Last updated: Recently

Model Type

MText

Max Context

300K

Max Output

5,120 tokens

Parameter Scale

300,000 token context window, maximum output of 5,120 tokens. Includes independent benchmarks from Artificial Analysis.

Input Modality

text, image

Output Modality

text

Inference Speed

210.908 tokens/s

Latest Release Date

12/3/2024

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Nova Lite

Release date

12/3/2024

Performance

210.908 tokens/s

model_creator.name

Amazon

AA Evaluation Scores

AA Intelligence Index

12.7

AA Coding Index

5.1

AA Math Index

MMLU Pro

0.59

GPQA

0.433

HLE

0.046

LiveCodeBench

0.167

SciCode

0.139

Math-500

0.764666666666667

AIME

0.106666666666667

AIME 2025

0.07

IFBench

0.341496598639456

LCR

0.176666666666667

TerminalBench Hard

0.00757575757575758

TAU2

0.175438596491228

Output Speed (tokens/s)

210.908 tok/s

TTFT (s)

0.698s

First Answer Token (s)

0.698s

Amazon

◎

Nova Lite

$0.06/M$0.24/M

300,000 token context window, maximum output of 5,120 tokens. Includes independent benchmarks from Artificial Analysis.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0