Saltar al contenido principal

GPT-5 (high)

OpenAIGPTProprietary

Descripción

GPT-5 is a flagship model from OpenAI designed for coding, reasoning, and agentic tasks across domains. It is optimized for coding and agentic tasks with higher reasoning capabilities and medium speed.

Fecha de lanzamiento
2025-08-07
Parámetros
Longitud del contexto
400K
Modalidades
file, image, text

Radar de capacidades

55
general
54
coding
95
reasoning
59
scienceest.
80
agents
90
multimodal

Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.

Rankings

Dominio#PosiciónPuntuaciónFuente
Agents & Tools57
55.0
LS
Code Ranking47
74.0
AA
General Ranking34
83.0
AA
Math Reasoning6
97.0
AA
Multimodal Ranking21
84.0
LS
Reasoning41
72.0
LS
Science41
74.0
AA

Puntuaciones de benchmarks (LLM Stats)

Agents

BrowseComp54.9%Aut.

Biology

GPQA85.7%Aut.

Code

SWE-Lancer (IC-Diamond subset)100.0%Aut.
HumanEval93.4%Aut.
Aider-Polyglot88.0%Aut.
SWE-Bench Verified74.9%Aut.

Communication

Tau2 Telecom96.7%Aut.
Tau2 Retail81.1%Aut.
Multi-Challenge69.6%Aut.
Tau2 Airline62.6%Aut.

Finance

MMLU92.5%Aut.

General

MMMU84.2%Aut.
MMMU-Pro78.4%Aut.
Internal API instruction following (hard)64.0%Aut.
LongFact Objects0.8%Aut.
LongFact Concepts0.7%Aut.

Healthcare

VideoMMMU84.6%Aut.
HealthBench Hard1.6%Aut.

Language

COLLIE99.0%Aut.

Long Context

OpenAI-MRCR: 2 needle 128k95.2%Aut.
OpenAI-MRCR: 2 needle 256k86.8%Aut.

Math

AIME 202594.6%Aut.
HMMT 202593.3%Aut.
MATH84.7%Aut.
FrontierMath26.3%Aut.
Humanity's Last Exam24.8%Aut.

Multimodal

VideoMME w sub.86.7%Aut.
CharXiv-R81.1%Aut.

Reasoning

BrowseComp Long Context 128k90.0%Aut.
BrowseComp Long Context 256k88.8%Aut.
Graphwalks BFS <128k78.3%Aut.
Graphwalks parents <128k73.3%Aut.
ERQA65.7%Aut.
FActScore1.0%Aut.

Índices de evaluación AA

Math Index
94.3
Intelligence Index
44.6
Coding Index
36.0
Math 500
1.0
Aime
1.0
Aime 25
0.9
Mmlu Pro
0.9
Gpqa
0.9
Tau2
0.8
Livecodebench
0.8
Lcr
0.8
Ifbench
0.7
Scicode
0.4
Terminalbench Hard
0.3
Hle
0.3

Puntuaciones por categoría LLM Stats

Robotics
20
Spatial Reasoning
6
Multimodal
4
Vision
3
Reasoning
2
Writing
100
Language
100
Long Context
100
Video
90
Biology
90
Chemistry
90
Code
90
Finance
90
Legal
90
Physics
90
Tool Calling
80
Communication
80
General
80
Frontend Development
70
Healthcare
70
Math
70
Search
70
Structured Output
60
Agents
50

Precios

Precio de entrada$1.25 / 1M tokens
Precio de salida$10 / 1M tokens
Precio mixto (3:1)$3.438 / 1M tokens

Velocidad

Tokens/seg95.3 tokens/s
Retraso del primer token98.86s
Tiempo hasta la respuesta98.86s

Proveedores disponibles

(Unidades internas LS)

No hay datos de proveedores disponibles

Fuentes externas