Saltar al contenido principal

Nova Micro

AmazonAmazonProprietary

Descripción

A text-only model that delivers lowest-latency responses at very low cost while maintaining strong performance on core language tasks. Optimized for speed and efficiency while preserving high accuracy on key benchmarks.

Fecha de lanzamiento
2024-12-03
Parámetros
Longitud del contexto
128K
Modalidades
text

Radar de capacidades

19
general
13
coding
19
reasoning
20
science
60
agents
0
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Ranking de codificación507
10.0
AA
Ranking general501
21.0
AA
Ciencia512
18.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)40.0%Aut.

Code

HumanEvalOpenAI (2021)81.1%Aut.

Economics

FinQA65.2%Aut.
CRAG43.1%Aut.

Finance

MMLU77.6%Aut.

General

ARC-C90.2%Aut.
IFEvalGoogle Research (2023)87.2%Aut.
BFCL56.2%Aut.

Language

Translation Set1→en COMET2288.7%Aut.
Translation en→Set1 COMET2288.5%Aut.
BBH79.5%Aut.
Translation Set1→en spBleu42.6%Aut.
Translation en→Set1 spBleu40.2%Aut.
SQuALITY18.8%Aut.

Math

GSM8k92.3%Aut.
DROP79.3%Aut.
MATH69.3%Aut.

Índices de evaluación AA

(Artificial Analysis)
Math Index(Artificial Analysis)
6.0
Intelligence Index(Artificial Analysis)
4.4
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.5
Gpqa(NYU + Cohere + Anthropic (2023))
0.4
Ifbench(Google Research (2023))
0.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.1
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.1
Lcr(Artificial Analysis)
0.1
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
Instruction Following
90
Legal
80
Math
80
Healthcare
80
Code
80
Reasoning
70
General
70
Language
60
Finance
60
Tool Calling
60
Economics
50
Physics
40
Search
40
Biology
40
Chemistry
40
Long Context
20
Summarization
20

Precios

Precio de entrada$0.035 / 1M tokens
Precio de salida$0.14 / 1M tokens
Precio mixto (3:1)$0.061 / 1M tokens
Precio de lectura caché$0.00875 / 1M tokens

Velocidad

Tokens/seg284.1
Retraso del primer token0.65s
Tiempo hasta la respuesta0.65s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

5 proveedores

Más barato: AmazonMás caro: NanoGPT
ProveedorEntradaSalida
1AmazonPRINCIPAL
$0.035
$0.14
2OpenRouter
$0.035
$0.14
3Kilo Gateway
$0.035
$0.14
4Amazon Bedrock
$0.035
$0.14
5NanoGPT
$0.0357
$0.1394

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas