Saltar al contenido principal

Nova Lite

AmazonAmazonProprietary

Descripción

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

Fecha de lanzamiento
2024-12-03
Parámetros
Longitud del contexto
300K
Modalidades
image, text, video

Radar de capacidades

22
general
16
coding
22
reasoning
25
science
70
agents
90
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Ranking de codificación479
14.0
AA
Ranking general466
26.0
AA
Ciencia489
23.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

MM-Mind2Web60.7%Aut.

Biology

GPQANYU + Cohere + Anthropic (2023)42.0%Aut.

Code

HumanEvalOpenAI (2021)85.4%Aut.

Economics

FinQA73.6%Aut.
CRAG43.8%Aut.

Finance

MMLU80.5%Aut.

Frontend Development

VisualWebBench77.7%Aut.

General

ARC-C92.4%Aut.
IFEvalGoogle Research (2023)89.7%Aut.
BFCL66.6%Aut.
MMMU56.2%Aut.

Grounding

GroundUI-1K80.2%Aut.

Image To Text

DocVQADocVQA (2020)92.4%Aut.
TextVQA80.2%Aut.

Language

Translation Set1→en COMET2288.8%Aut.
Translation en→Set1 COMET2288.8%Aut.
BBH82.4%Aut.
VATEX77.8%Aut.
Translation Set1→en spBleu43.1%Aut.
Translation en→Set1 spBleu41.5%Aut.
SQuALITY19.2%Aut.

Long Context

EgoSchema71.4%Aut.
LVBench40.4%Aut.

Math

GSM8k94.5%Aut.
DROP80.2%Aut.
MATH73.3%Aut.

Multimodal

ChartQAMasry et al. (2022)86.8%Aut.

Índices de evaluación AA

(Artificial Analysis)
Math Index(Artificial Analysis)
7.0
Intelligence Index(Artificial Analysis)
6.7
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.8
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.6
Gpqa(NYU + Cohere + Anthropic (2023))
0.4
Ifbench(Google Research (2023))
0.3
Lcr(Artificial Analysis)
0.2
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.2
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.2
Scicode(UIUC + Argonne National Lab (2024))
0.1
Aime(MAA (Mathematical Association of America))
0.1
Aime 25(MAA (Mathematical Association of America))
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.0
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Structured Output
90
Image To Text
90
Instruction Following
90
Code
90
Legal
80
Math
80
Multimodal
70
Reasoning
70
Finance
70
General
70
Healthcare
70
Tool Calling
70
Vision
70
Language
60
Frontend Development
60
Agents
60
Economics
60
Long Context
40
Physics
40
Search
40
Biology
40
Chemistry
40
Summarization
20

Precios

Precio de entrada$0.06 / 1M tokens
Precio de salida$0.24 / 1M tokens
Precio mixto (3:1)$0.105 / 1M tokens
Precio de lectura caché$0.015 / 1M tokens

Velocidad

Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

5 proveedores

Más barato: NanoGPTMás caro: Amazon Bedrock
ProveedorEntradaSalida
1NanoGPTMás barato
$0.0595
$0.238
2AmazonPRINCIPAL
$0.06
$0.24
3OpenRouter
$0.06
$0.24
4Kilo Gateway
$0.06
$0.24
5Amazon Bedrock
$0.06
$0.24

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas