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 | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Agents & Tools | 43 | 58.0 | LS |
| Code Ranking | 12 | 87.0 | AA |
| General Ranking | 16 | 88.0 | AA |
| Math Reasoning | 2 | 100.0 | AA |
| Multimodal Ranking | 24 | 82.0 | LS |
| Reasoning | 27 | 82.0 | LS |
| Science | 13 | 87.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
Agents
BrowseComp
65.8%Aut.
MCP Atlas
60.6%Aut.
Toolathlon
46.3%Aut.
Biology
GPQA
92.4%Aut.
Code
SWE-Bench Verified
80.0%Aut.
SWE-Lancer (IC-Diamond subset)
74.6%Aut.
Communication
Tau2 Telecom
98.7%Aut.
Tau2 Retail
82.0%Aut.
General
MMMLU
89.6%Aut.
MMMU-Pro
79.5%Aut.
Grounding
ScreenSpot Pro
86.3%Aut.
Healthcare
VideoMMMU
85.9%Aut.
Math
AIME 2025
100.0%Aut.
HMMT 2025
99.4%Aut.
FrontierMath
40.3%Aut.
Humanity's Last Exam
34.5%Aut.
Multimodal
CharXiv-R
82.1%Aut.
Reasoning
Graphwalks BFS <128k
94.0%Aut.
BrowseComp Long Context 128k
92.0%Aut.
BrowseComp Long Context 256k
89.8%Aut.
Graphwalks parents <128k
89.0%Aut.
ARC-AGI
86.2%Aut.
ARC-AGI v2
52.9%Aut.
Índices de evaluación AA
Math Index99.0
Intelligence Index51.3
Coding Index48.7
Aime 251.0
Gpqa0.9
Livecodebench0.9
Mmlu Pro0.9
Tau20.8
Ifbench0.8
Lcr0.7
Scicode0.5
Terminalbench Hard0.5
Hle0.4
Puntuaciones por categoría LLM Stats
Biology90
Chemistry90
Communication90
General90
Grounding90
Healthcare90
Language90
Physics90
Spatial Reasoning80
Frontend Development80
Multimodal80
Reasoning80
Search80
Tool Calling70
Vision70
Code70
Math70
Agents60
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)| Proveedor | Precio de entrada | Precio de salida |
|---|---|---|
| OpenAI | 1.8M | 14.0M |