Nova Pro
AmazonAmazonProprietary
Descripción
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.
Fecha de lanzamiento
2024-12-03
Parámetros
—
Longitud del contexto
300K
Modalidades
image, pdf, text, video
Radar de capacidades
25
general
23
coding
23
reasoning
36
science
70
agents
90
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Ranking de codificación | 518 | 19.0 | AA |
| Ranking general | 499 | 28.0 | AA |
| Ranking multimodal | 128 | 35.0 | LS |
| Ciencia | 525 | 25.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Chat
IFEvalGoogle Research (2023)
92.1%Aut.
Finance
FinQA
77.2%Aut.
General
MMLU
85.9%Aut.
BFCL
68.4%Aut.
Language
Translation en→Set1 COMET22
89.1%Aut.
Translation Set1→en COMET22
89.0%Aut.
Translation Set1→en spBleu
44.4%Aut.
Translation en→Set1 spBleu
43.4%Aut.
Math
GSM8k
94.8%Aut.
MATH
76.6%Aut.
Multimodal
GroundUI-1K
81.4%Aut.
VATEX
77.8%Aut.
MM-Mind2Web
63.7%Aut.
MMMU
61.7%Aut.
Reasoning
ARC-C
94.8%Aut.
ChartQAMasry et al. (2022)
89.2%Aut.
HumanEvalOpenAI (2021)
89.0%Aut.
BBH
86.9%Aut.
DROP
85.4%Aut.
CRAG
50.3%Aut.
GPQANYU + Cohere + Anthropic (2023)
46.9%Aut.
Summarization
SQuALITY
19.8%Aut.
Vision
DocVQADocVQA (2020)
93.5%Aut.
TextVQA
81.5%Aut.
VisualWebBench
79.7%Aut.
EgoSchema
72.1%Aut.
LVBench
41.6%Aut.
Índices de evaluación AA
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))78.6
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))69.1
Gpqa(NYU + Cohere + Anthropic (2023))49.9
Ifbench(Google Research (2023))38.1
Livecodebench(UC Berkeley + MIT + Cornell (2024))23.3
Lcr(Artificial Analysis)21.0
Tau2(Sierra + U Toronto + Vector Institute (2025))14.0
Aime(MAA (Mathematical Association of America))10.7
Aime 25(MAA (Mathematical Association of America))7.0
Intelligence Index(Artificial Analysis)7.0
Math Index(Artificial Analysis)7.0
Terminalbench Hard(Stanford × Laude Institute (2026))6.1
Hle(Center for AI Safety + Scale AI (2025))3.2
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Chat90
Image To Text90
Instruction Following90
Legal90
Structured Output90
Code90
Math80
Reasoning80
Language70
Multimodal70
Finance70
General70
Healthcare70
Tool Calling70
Vision70
Frontend Development60
Agents60
Economics60
Physics50
Search50
Biology50
Chemistry50
Long Context40
Summarization20
Precios
Precio de entrada$0.8 / 1M tokens
Precio de salida$3.2 / 1M tokens
Precio mixto (3:1)$1.4 / 1M tokens
Precio de lectura caché$0.2 / 1M tokens
Precio de escritura caché$0.8 / 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
2 proveedores
Más barato: AmazonMás caro: Amazon Bedrock
ProveedorEntradaSalida
1AmazonPRINCIPAL
$0.8
$3.2
2Amazon Bedrock
$0.8
$3.2
Comparar precios entre diferentes proveedores de API para este modelo.