GPT-4.1 nano
OpenAIGPTProprietary
Descripción
GPT-4.1 nano is OpenAI's fastest and cheapest model available in the GPT-4.1 family. It delivers exceptional performance at a small size with its 1 million token context window. Ideal for tasks like classification or autocompletion.
Fecha de lanzamiento
2025-04-14
Parámetros
—
Longitud del contexto
1.0M
Modalidades
file, image, text
Radar de capacidades
27
general
20
coding
36
reasoning
33
scienceest.
10
agents
85
multimodal
Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Code Ranking | 341 | 20.0 | AA |
| General Ranking | 375 | 29.0 | AA |
| Math Reasoning | 242 | 36.0 | AA |
| Multimodal Ranking | 69 | 60.0 | LS |
| Reasoning | 102 | 17.0 | LS |
| Science | 329 | 33.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
Biology
GPQA
50.3%Aut.
Code
Aider-Polyglot
9.8%Aut.
Aider-Polyglot Edit
6.2%Aut.
Communication
Multi-IF
57.2%Aut.
TAU-bench Retail
22.6%Aut.
Multi-Challenge
15.0%Aut.
TAU-bench Airline
14.0%Aut.
Finance
MMLU
80.1%Aut.
General
IFEval
74.5%Aut.
MMMLU
66.9%Aut.
MMMU
55.4%Aut.
Internal API instruction following (hard)
31.6%Aut.
Language
COLLIE
42.5%Aut.
Long Context
OpenAI-MRCR: 2 needle 128k
36.6%Aut.
OpenAI-MRCR: 2 needle 1M
12.0%Aut.
ComplexFuncBench
5.7%Aut.
Graphwalks parents >128k
5.6%Aut.
Graphwalks BFS >128k
2.9%Aut.
Math
MathVista
56.2%Aut.
AIME 2024
29.4%Aut.
Multimodal
CharXiv-D
73.9%Aut.
CharXiv-R
40.5%Aut.
Reasoning
Graphwalks BFS <128k
25.0%Aut.
Graphwalks parents <128k
9.4%Aut.
Índices de evaluación AA
Math Index24.0
Intelligence Index13.0
Coding Index11.2
Math 5000.8
Mmlu Pro0.7
Gpqa0.5
Livecodebench0.3
Ifbench0.3
Scicode0.3
Aime 250.2
Aime0.2
Tau20.2
Lcr0.2
Hle0.0
Terminalbench Hard0.0
Puntuaciones por categoría LLM Stats
Finance80
Legal80
Healthcare70
Instruction Following70
Vision60
Language60
Math60
Multimodal60
Structured Output50
Biology50
Chemistry50
General50
Physics50
Writing40
Communication30
Reasoning30
Spatial Reasoning10
Tool Calling10
Code10
Long Context10
Precios
Precio de entrada$0.1 / 1M tokens
Precio de salida$0.4 / 1M tokens
Precio mixto (3:1)$0.175 / 1M tokens
Velocidad
Tokens/seg121.7 tokens/s
Retraso del primer token0.52s
Tiempo hasta la respuesta0.52s
Proveedores disponibles
(Unidades internas LS)| Proveedor | Precio de entrada | Precio de salida |
|---|---|---|
| OpenAI | 100K | 400K |