Saltar al contenido principal

o3

OpenAIOpenAI o-seriesProprietary

Descripción

OpenAI's most powerful reasoning model. o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.

Fecha de lanzamiento
2025-04-16
Parámetros
Longitud del contexto
200K
Modalidades
image, pdf, text

Radar de capacidades

46
general
72
coding
90
reasoning
56
science
70
agents
85
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica133
33.0
LS
Ranking de codificación71
77.0
AA
Ranking general96
71.0
AA
Ranking multimodal38
51.0
LS
Ciencia140
63.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

Tau-bench63.0%Aut.
BrowseCompOpenAI (2025)49.7%Aut.

Biology

GPQANYU + Cohere + Anthropic (2023)83.3%Aut.

Code

Aider-Polyglot81.3%Aut.
SWE-Bench Verified69.1%Aut.

Communication

Tau2 Retail80.2%Aut.
Tau2 Airline64.8%Aut.
Multi-Challenge60.4%Aut.
Tau2 Telecom58.2%Aut.

General

MMMU82.9%Aut.
MMMU-Pro76.4%Aut.

Healthcare

VideoMMMU83.3%Aut.

Language

COLLIE98.4%Aut.

Math

AIME 202491.6%Aut.
MathVista86.8%Aut.
AIME 202586.4%Aut.
FrontierMath15.8%Aut.
Humanity's Last Exam14.7%Aut.

Multimodal

CharXiv-R78.6%Aut.

Reasoning

ARC-AGI88.0%Aut.
ERQA64.0%Aut.
ARC-AGI v26.5%

Índices de evaluación AA

(Artificial Analysis)
Math Index(Artificial Analysis)
88.3
Intelligence Index(Artificial Analysis)
31.1
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
1.0
Aime(MAA (Mathematical Association of America))
0.9
Aime 25(MAA (Mathematical Association of America))
0.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.8
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.8
Lcr(Artificial Analysis)
0.7
Ifbench(Google Research (2023))
0.7
Scicode(UIUC + Argonne National Lab (2024))
0.4
Terminalbench Hard(Stanford × Laude Institute (2026))
0.4
Hle(Center for AI Safety + Scale AI (2025))
0.2

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Language
100
Writing
100
Multimodal
80
Physics
80
Healthcare
80
Biology
80
Chemistry
80
Code
80
Reasoning
70
Frontend Development
70
General
70
Communication
70
Tool Calling
70
Math
60
Agents
60
Vision
60
Search
50
Spatial Reasoning
50

Precios

Precio de entrada$2 / 1M tokens
Precio de salida$8 / 1M tokens
Precio mixto (3:1)$3.5 / 1M tokens
Precio de lectura caché$0.5 / 1M tokens

Velocidad

Tokens/seg106.2
Retraso del primer token7.90s
Tiempo hasta la respuesta7.90s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

16 proveedores

Más barato: PoeMás caro: Jiekou.AI
ProveedorEntradaSalida
1PoeMás barato
$1.8
$7.2
2OpenAIPRINCIPAL
$2
$8
3NanoGPT
$2
$8
4Abacus
$2
$8
5OpenRouter
$2
$8
6Kilo Gateway
$2
$8
7Cloudflare AI Gateway
$2
$8
8Helicone
$2
$8
9Azure Cognitive Services
$2
$8
10Vercel AI Gateway
$2
$8
11LLM Gateway
$2
$8
12Azure
$2
$8
13NEAR AI Cloud
$2
$8
14Merge Gateway
$2
$8
15Impossibl
$2
$8
16Jiekou.AI
$10
$40

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas