GPT-5.1 (Non-reasoning)
OpenAIGPTProprietary
Описание
GPT-5.1 Instant is the next iteration of GPT-5, designed to be more conversational than earlier chat models. It features improved instruction following and an adaptive reasoning capability that lets it decide when to think before responding. GPT-5.1 Instant offers clearer and more engaging interactions, reducing jargon and enhancing user comprehension. It demonstrates significant improvements in coding tasks, making it a valuable tool for developers. GPT-5.1 Auto routes each query to the model best suited for it, so users typically don't need to choose a model manually.
Дата выхода
2025-11-13
Параметры
—
Длина контекста
400K
Модальности
image, text
Радар способностей
32
general
49
coding
42
reasoning
46
science
80
agents
90
multimodal
Рейтинги
| Домен | #Место | Оценка | Источник |
|---|---|---|---|
| Рейтинг кодинга | 326 | 46.0 | AA |
| Общий рейтинг | 301 | 43.0 | AA |
| Мультимодальный рейтинг | 18 | 64.0 | LS |
| Наука | 420 | 35.0 | AA |
Оценки бенчмарков (LLM Stats)
(LLM Stats (zeroeval))Chat
Tau2 Airline
67.0%Сам.
Communication
Tau2 Telecom
95.6%Сам.
Tau2 Retail
77.9%Сам.
Math
AIME 2025
98.4%Сам.
FrontierMath
26.7%Сам.
Multimodal
MMMU
85.4%Сам.
Reasoning
BrowseComp Long Context 128k
90.0%Сам.
GPQANYU + Cohere + Anthropic (2023)
88.1%Сам.
SWE-Bench Verified
76.3%Сам.
Индексы оценки AA
(Artificial Analysis)Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))80.1
Gpqa(NYU + Cohere + Anthropic (2023))64.3
Livecodebench(UC Berkeley + MIT + Cornell (2024))49.4
Tau2(Sierra + U Toronto + Vector Institute (2025))46.5
Lcr(Artificial Analysis)45.0
Ifbench(Google Research (2023))43.2
Math Index(Artificial Analysis)38.0
Aime 25(MAA (Mathematical Association of America))38.0
Terminalbench Hard(Stanford × Laude Institute (2026))22.7
Intelligence Index(Artificial Analysis)13.3
Hle(Center for AI Safety + Scale AI (2025))5.3
Оценки категорий LLM Stats
(LLM Stats (zeroeval))Multimodal90
Physics90
Search90
Healthcare90
Biology90
Chemistry90
Vision90
Reasoning80
Frontend Development80
General80
Code80
Communication80
Tool Calling80
Chat70
Math60
Цены
Цена ввода$1.25 / 1M токенов
Цена вывода$10 / 1M токенов
Смешанная цена (3:1)$3.438 / 1M токенов
Цена чтения кэша$0.125 / 1M токенов
Скорость
Токенов/сек0.0
Задержка первого токена0.00s
Время до первого ответа0.00s
Рейтинг цен провайдеров
Рейтинг цен провайдеров
12 провайдеров
Самый дешевый: OpenAIСамый дорогой: Cortecs
ПровайдерВводВывод
1OpenAIСамый дешевый
$0
$0.00001
2OpenCode Zen
$1.07
$8.5
3Jiekou.AI
$1.125
$9
4302.AI
$1.25
$10
5Abacus
$1.25
$10
6Helicone
$1.25
$10
7AIHubMix
$1.25
$10
8Azure Cognitive Services
$1.25
$10
9DevPass (LLM Gateway)
$1.25
$10
10Azure
$1.25
$10
11Pioneer
$1.25
$10
12Cortecs
$1.375
$10.96
Сравнение цен разных API-провайдеров для этой модели.