Saltar al contenido principal

Phi-4 Mini Instruct

MicrosoftPhiOpen WeightMIT · Uso Comercial

Descripción

Phi 4 Mini Instruct is a lightweight (3.8B parameters) open model built upon synthetic data and filtered web data, focusing on high-quality reasoning. It supports a 128K token context length and is enhanced for instruction adherence and safety via supervised fine-tuning and direct preference optimization.

Fecha de lanzamiento
2024-02-26
Parámetros
3.8B
Longitud del contexto
Modalidades

Radar de capacidades

18
general
8
coding
18
reasoning
20
science
15
agents
0
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Ranking de codificación515
9.0
AA
Ranking general526
17.0
AA
Ciencia518
17.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)52.0%Aut.

Creativity

Social IQa72.5%Aut.
Arena Hard32.8%Aut.

Finance

MMLU67.3%Aut.
TruthfulQA66.4%Aut.
MMLU-Pro52.8%Aut.

General

ARC-C83.7%Aut.
OpenBookQA79.2%Aut.
PIQA77.6%Aut.
Multilingual MMLU49.3%Aut.

Language

BoolQ81.2%Aut.
BIG-Bench Hard70.4%Aut.
Winogrande67.0%Aut.

Math

MATH-50094.6%Aut.
GSM8k88.6%Aut.
MATH64.0%Aut.
MGSM63.9%Aut.
AIMEMAA57.5%Aut.

Reasoning

HellaSwagAI2 (2019)69.1%Aut.

Índices de evaluación AA

(Artificial Analysis)
Math Index(Artificial Analysis)
6.7
Intelligence Index(Artificial Analysis)
5.7
Coding Index(Artificial Analysis)
3.8
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))
0.3
Ifbench(Google Research (2023))
0.2
Lcr(Artificial Analysis)
0.2
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.1
Scicode(UIUC + Argonne National Lab (2024))
0.1
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.1
Aime 25(MAA (Mathematical Association of America))
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.0
Aime(MAA (Mathematical Association of America))
0.0
Terminalbench V2 1
0.0
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Math
70
Psychology
70
Reasoning
70
General
70
Legal
60
Language
60
Finance
60
Healthcare
60
Physics
50
Creativity
50
Biology
30
Chemistry
30
Writing
30

Precios

Precio de entradaGratis
Precio de salidaGratis
Precio mixto (3:1)Gratis

Velocidad

Tokens/seg45.1
Retraso del primer token0.34s
Tiempo hasta la respuesta0.34s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

2 proveedores

Más barato: Azure Cognitive ServicesMás caro: Azure
ProveedorEntradaSalida
1Azure Cognitive ServicesMás barato
$0.075
$0.3
2Azure
$0.075
$0.3

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas