Phi-4
MicrosoftPhiOpen WeightMIT · Uso Comercial
Descripción
phi-4 is a state-of-the-art open model built to excel at advanced reasoning, coding, and knowledge tasks. It leverages a blend of synthetic data, filtered web data, academic texts, and supervised fine-tuning for precision, alignment, and safety.
Fecha de lanzamiento
2024-12-12
Parámetros
14.7B
Longitud del contexto
16K
Modalidades
text
Radar de capacidades
25
general
23
coding
30
reasoning
41
science
28
agents
0
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Ranking de codificación | 586 | 10.0 | AA |
| Ranking general | 569 | 21.0 | AA |
| Ciencia | 475 | 30.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Chat
IFEvalGoogle Research (2023)
83.4%Aut.
Factuality
SimpleQA
3.0%Aut.
General
MMLU
84.8%Aut.
Arena Hard
73.3%Aut.
Language
MMLU-Pro
74.3%Aut.
Math
MGSM
80.6%Aut.
MATH
80.4%Aut.
OmniMath
76.6%Aut.
AIME 2024
75.3%Aut.
AIME 2025
62.9%Aut.
LiveBench
47.6%Aut.
Reasoning
FlenQA
97.7%Aut.
HumanEval+
92.9%Aut.
HumanEvalOpenAI (2021)
82.6%Aut.
DROP
75.5%Aut.
PhiBench
70.6%Aut.
GPQANYU + Cohere + Anthropic (2023)
65.8%Aut.
LiveCodeBench
53.8%Aut.
Índices de evaluación AA
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))81.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))71.4
Gpqa(NYU + Cohere + Anthropic (2023))57.5
Ifbench(Google Research (2023))23.5
Livecodebench(UC Berkeley + MIT + Cornell (2024))23.1
Math Index(Artificial Analysis)18.0
Aime 25(MAA (Mathematical Association of America))18.0
Aime(MAA (Mathematical Association of America))14.3
Intelligence Index(Artificial Analysis)5.9
Hle(Center for AI Safety + Scale AI (2025))3.8
Terminalbench Hard(Stanford × Laude Institute (2026))3.8
Lcr(Artificial Analysis)0.0
Tau2(Sierra + U Toronto + Vector Institute (2025))0.0
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Language80
Legal80
Finance80
Healthcare80
Code80
Creativity80
Writing80
Chat70
Math70
Reasoning70
General70
Instruction Following60
Physics60
Structured Output60
Biology60
Chemistry60
Factuality0
Precios
Precio de entrada$0.125 / 1M tokens
Precio de salida$0.5 / 1M tokens
Precio mixto (3:1)$0.219 / 1M tokens
Velocidad
Tokens/seg43.9
Retraso del primer token0.98s
Tiempo hasta la respuesta0.98s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
6 proveedores
Más barato: DeepInfraMás caro: Azure
ProveedorEntradaSalida
1DeepInfraMás barato
$0
$0
2OpenRouter
$0.07
$0.14
3Kilo Gateway
$0.07
$0.14
4MicrosoftPRINCIPAL
$0.125
$0.5
5Azure Cognitive Services
$0.125
$0.5
6Azure
$0.125
$0.5
Comparar precios entre diferentes proveedores de API para este modelo.