GPT-5.2 (xhigh)
OpenAIGPTProprietary
Описание
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.
Дата выхода
2025-12-11
Параметры
—
Длина контекста
400K
Модальности
file, image, text
Радар способностей
60
general
63
coding
98
reasoning
66
scienceоцен.
70
agents
85
multimodal
Science использует прокси на основе рассуждений, когда специализированные научные бенчмарки недоступны.
Рейтинги
| Домен | #Место | Оценка | Источник |
|---|---|---|---|
| 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 |
Оценки бенчмарков (LLM Stats)
Agents
BrowseComp
65.8%Сам.
MCP Atlas
60.6%Сам.
Toolathlon
46.3%Сам.
Biology
GPQA
92.4%Сам.
Code
SWE-Bench Verified
80.0%Сам.
SWE-Lancer (IC-Diamond subset)
74.6%Сам.
Communication
Tau2 Telecom
98.7%Сам.
Tau2 Retail
82.0%Сам.
General
MMMLU
89.6%Сам.
MMMU-Pro
79.5%Сам.
Grounding
ScreenSpot Pro
86.3%Сам.
Healthcare
VideoMMMU
85.9%Сам.
Math
AIME 2025
100.0%Сам.
HMMT 2025
99.4%Сам.
FrontierMath
40.3%Сам.
Humanity's Last Exam
34.5%Сам.
Multimodal
CharXiv-R
82.1%Сам.
Reasoning
Graphwalks BFS <128k
94.0%Сам.
BrowseComp Long Context 128k
92.0%Сам.
BrowseComp Long Context 256k
89.8%Сам.
Graphwalks parents <128k
89.0%Сам.
ARC-AGI
86.2%Сам.
ARC-AGI v2
52.9%Сам.
Индексы оценки 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
Оценки категорий LLM Stats
Biology90
Chemistry90
Communication90
General90
Grounding90
Healthcare90
Language90
Physics90
Spatial Reasoning80
Frontend Development80
Multimodal80
Reasoning80
Search80
Tool Calling70
Vision70
Code70
Math70
Agents60
Цены
Цена ввода$1.75 / 1M tokens
Цена вывода$14 / 1M tokens
Смешанная цена (3:1)$4.813 / 1M tokens
Скорость
Токенов/сек72.2 tokens/s
Задержка первого токена93.90s
Время до первого ответа93.90s
Доступные провайдеры
(Внутренние единицы LS)| Провайдер | Цена ввода | Цена вывода |
|---|---|---|
| OpenAI | 1.8M | 14.0M |