Passer au contenu principal

Nova Pro

AmazonAmazonProprietary

Description

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.

Date de sortie
2024-12-03
Paramètres
Longueur du contexte
300K
Modalités
image, text, video

Radar de capacités

25
general
23
coding
23
reasoning
30
science
70
agents
90
multimodal

Classements

Domaine#RangScoreSource
Classement codage426
20.0
AA
Classement général446
29.0
AA
Science447
29.0
AA

Scores de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

MM-Mind2Web63.7%Aut.

Biology

GPQANYU + Cohere + Anthropic (2023)46.9%Aut.

Code

HumanEvalOpenAI (2021)89.0%Aut.

Economics

FinQA77.2%Aut.
CRAG50.3%Aut.

Finance

MMLU85.9%Aut.

Frontend Development

VisualWebBench79.7%Aut.

General

ARC-C94.8%Aut.
IFEvalGoogle Research (2023)92.1%Aut.
BFCL68.4%Aut.
MMMU61.7%Aut.

Grounding

GroundUI-1K81.4%Aut.

Image To Text

DocVQADocVQA (2020)93.5%Aut.
TextVQA81.5%Aut.

Language

Translation en→Set1 COMET2289.1%Aut.
Translation Set1→en COMET2289.0%Aut.
BBH86.9%Aut.
VATEX77.8%Aut.
Translation Set1→en spBleu44.4%Aut.
Translation en→Set1 spBleu43.4%Aut.
SQuALITY19.8%Aut.

Long Context

EgoSchema72.1%Aut.
LVBench41.6%Aut.

Math

GSM8k94.8%Aut.
DROP85.4%Aut.
MATH76.6%Aut.

Multimodal

ChartQAMasry et al. (2022)89.2%Aut.

Indices d'évaluation AA

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
7.5
Math Index(Artificial Analysis)
7.0
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.8
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.7
Gpqa(NYU + Cohere + Anthropic (2023))
0.5
Ifbench(Google Research (2023))
0.4
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.2
Lcr(Artificial Analysis)
0.2
Scicode(UIUC + Argonne National Lab (2024))
0.2
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.1
Aime(MAA (Mathematical Association of America))
0.1
Aime 25(MAA (Mathematical Association of America))
0.1
Terminalbench Hard(Stanford × Laude Institute (2026))
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.0

Scores par catégorie LLM Stats

(LLM Stats (zeroeval))
Legal
90
Structured Output
90
Image To Text
90
Instruction Following
90
Code
90
Math
80
Reasoning
80
Multimodal
70
Language
70
Finance
70
General
70
Healthcare
70
Tool Calling
70
Vision
70
Frontend Development
60
Agents
60
Economics
60
Physics
50
Search
50
Biology
50
Chemistry
50
Long Context
40
Summarization
20

Tarification

Prix d'entrée$0.8 / 1M tokens
Prix de sortie$3.2 / 1M tokens
Prix mixte (3:1)$1.4 / 1M tokens
Prix de lecture cache$0.2 / 1M tokens

Vitesse

Tokens/sec0.0
Délai du premier token0.00s
Temps de réponse0.00s

Classement des Prix par Fournisseur

Classement des Prix par Fournisseur

2 fournisseurs

Moins cher: AmazonPlus cher: Amazon Bedrock
FournisseurEntréeSortie
1AmazonPRINCIPAL
$0.8
$3.2
2Amazon Bedrock
$0.8
$3.2

Comparer les prix entre différents fournisseurs API pour ce modèle.

Sources externes