Saltar al contenido principal

GPT-5.2 (xhigh)

OpenAIGPTProprietary

Descripción

GPT‑5.2 introduces substantial gains in professional knowledge work, outperforming experts on GDPval with 70.9% wins or ties, and setting new highs in coding (SWE‑Bench Pro 55.6%), science (GPQA Diamond ~92–93%), math (AIME 2025: 100%), long‑context accuracy up to 256k tokens, and reliable tool‑calling (Tau2 Telecom 98.7%). It rolls out as Instant, Thinking, and Pro—faster, more structured, and less error‑prone—priced at $1.75/1M input and $14/1M output tokens, with Pro variants supporting xhigh reasoning for top‑quality, end‑to‑end execution.

Fecha de lanzamiento
2025-12-11
Parámetros
Longitud del contexto
400K
Modalidades
file, image, text

Radar de capacidades

60
general
63
coding
98
reasoning
66
scienceest.
70
agents
85
multimodal

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

Rankings

Dominio#PosiciónPuntuaciónFuente
Agents & Tools43
58.0
LS
Code Ranking12
87.0
AA
General Ranking16
88.0
AA
Math Reasoning2
100.0
AA
Multimodal Ranking24
82.0
LS
Reasoning27
82.0
LS
Science13
87.0
AA

Puntuaciones de benchmarks (LLM Stats)

Agents

BrowseComp65.8%Aut.
MCP Atlas60.6%Aut.
Toolathlon46.3%Aut.

Biology

GPQA92.4%Aut.

Code

SWE-Bench Verified80.0%Aut.
SWE-Lancer (IC-Diamond subset)74.6%Aut.

Communication

Tau2 Telecom98.7%Aut.
Tau2 Retail82.0%Aut.

General

MMMLU89.6%Aut.
MMMU-Pro79.5%Aut.

Grounding

ScreenSpot Pro86.3%Aut.

Healthcare

VideoMMMU85.9%Aut.

Math

AIME 2025100.0%Aut.
HMMT 202599.4%Aut.
FrontierMath40.3%Aut.
Humanity's Last Exam34.5%Aut.

Multimodal

CharXiv-R82.1%Aut.

Reasoning

Graphwalks BFS <128k94.0%Aut.
BrowseComp Long Context 128k92.0%Aut.
BrowseComp Long Context 256k89.8%Aut.
Graphwalks parents <128k89.0%Aut.
ARC-AGI86.2%Aut.
ARC-AGI v252.9%Aut.

Índices de evaluación AA

Math Index
99.0
Intelligence Index
51.3
Coding Index
48.7
Aime 25
1.0
Gpqa
0.9
Livecodebench
0.9
Mmlu Pro
0.9
Tau2
0.8
Ifbench
0.8
Lcr
0.7
Scicode
0.5
Terminalbench Hard
0.5
Hle
0.4

Puntuaciones por categoría LLM Stats

Biology
90
Chemistry
90
Communication
90
General
90
Grounding
90
Healthcare
90
Language
90
Physics
90
Spatial Reasoning
80
Frontend Development
80
Multimodal
80
Reasoning
80
Search
80
Tool Calling
70
Vision
70
Code
70
Math
70
Agents
60

Precios

Precio de entrada$1.75 / 1M tokens
Precio de salida$14 / 1M tokens
Precio mixto (3:1)$4.813 / 1M tokens

Velocidad

Tokens/seg72.2 tokens/s
Retraso del primer token93.90s
Tiempo hasta la respuesta93.90s

Proveedores disponibles

(Unidades internas LS)
ProveedorPrecio de entradaPrecio de salida
OpenAI1.8M14.0M

Fuentes externas