Перейти к основному содержанию
AITier

GPT-5.6 Sol (max)

OpenAIGPTProprietary

Описание

GPT-5.6 Sol is the frontier model in OpenAI's GPT-5.6 family, designed for complex professional work across coding, knowledge work, cybersecurity, and science. It sets state-of-the-art results while using fewer tokens at lower estimated cost, supports max reasoning effort and an ultra multi-agent mode, and has a 1.05M-token context window. The gpt-5.6 alias routes to GPT-5.6 Sol.

Дата выхода
2026-07-09
Параметры
—
Длина контекста
1.1M
Модальности
image, pdf, text

Радар способностей

58
general
74
coding
94
reasoning
72
science
70
agents
85
multimodal

Рейтинги

Домен#МестоОценкаИсточник
Агентные возможности2
80.0
LS
Рейтинг кодинга1
98.0
AA
Общий рейтинг10
91.0
AA
Мультимодальный рейтинг10
66.0
LS
Наука5
94.0
AA

Оценки бенчмарков (LLM Stats)

(LLM Stats (zeroeval))

Agents

Connectors100.0%Сам.
Capture-the-Flag Challenges (Internal)96.7%Сам.
Search and Function-Calling91.0%Сам.
SEC-bench Pro71.2%Сам.
Internal Research Debugging Evaluation68.3%Сам.
KernelGen 1P61.1%Сам.
LifeSciBench59.9%Сам.
Toolathlon58.0%Сам.
RSI Index57.9%Сам.
Big Finance Bench53.0%Сам.
Agents' Last Exam52.7%Сам.
PostTrainBench Lite50.3%Сам.
Management Consulting Tasks (Internal)43.2%Сам.
ExploitGym33.7%Сам.
GeneBench-Pro28.7%Сам.
AutomationBench18.1%Сам.
NanoGPT9.7%Сам.

Code

BenchCAD (with Python tool)83.4%Сам.
ExploitBench73.5%Сам.
DeepSWE 1.173.0%
DeepSWE72.7%Сам.
BenchCAD70.6%Сам.

General

Artificial Analysis59.0%
GDP.pdf30.7%Сам.

Healthcare

HealthBench Consensus95.5%Сам.
HealthBench Professional60.5%Сам.
HealthBench57.0%Сам.
HealthBench Hard33.1%Сам.

Long Context

MRCR v2 (8-needle)91.5%Сам.
MRCR v2 (8-needle, 512K-1M)73.8%Сам.

Math

FrontierMath89.0%Сам.
FrontierMath Tier 4 (v2)83.0%Сам.

Multimodal

OSWorld 2.062.6%Сам.

Reasoning

GPQANYU + Cohere + Anthropic (2023)94.6%Сам.
Graphwalks BFS >128k90.7%Сам.
BrowseCompOpenAI (2025)90.4%Сам.
Terminal-Bench 2.188.8%Сам.
Graphwalks BFS 1M77.1%Сам.
SWE-Bench ProPrinceton NLP (2024)64.6%Сам.
MedChemBench (Internal)48.3%Сам.
FrontierCode 1.147.5%
ARC-AGI-37.8%Сам.

Vision

MMMU-Pro (with tools)84.6%Сам.
MMMU-Pro83.0%Сам.

Индексы оценки AA

(Artificial Analysis)
Coding Index(Artificial Analysis)
77.4
Intelligence Index(Artificial Analysis)
60.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.9
Terminalbench V2 1
0.9
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.9
Lcr(Artificial Analysis)
0.8
Ifbench(Google Research (2023))
0.7
Terminalbench Hard(Stanford × Laude Institute (2026))
0.7
Scicode(UIUC + Argonne National Lab (2024))
0.6
Hle(Center for AI Safety + Scale AI (2025))
0.5
Tau Banking
0.4

Оценки категорий LLM Stats

(LLM Stats (zeroeval))
Math
90
Physics
90
Search
90
Biology
90
Chemistry
90
Long Context
80
Spatial Reasoning
80
Multimodal
70
Safety
70
Tool Calling
70
Vision
70
Reasoning
60
General
60
Healthcare
60
Agents
60
Code
60
Science
50
Finance
50
Systems
40

Цены

Цена ввода$5 / 1M токенов
Цена вывода$30 / 1M токенов
Смешанная цена (3:1)$11.25 / 1M токенов
Цена чтения кэша$0.5 / 1M токенов
Цена записи кэша$6.25 / 1M токенов

Скорость

Токенов/сек74.9
Задержка первого токена108.11s
Время до первого ответа108.11s

Рейтинг цен провайдеров

Рейтинг цен провайдеров

2 провайдеров

Самый дешевый: OpenAIСамый дорогой: Neon
ПровайдерВводВывод
1OpenAIСамый дешевый
$0.00001
$0.00003
2Neon
$5
$30

Сравнение цен разных API-провайдеров для этой модели.

Внешние ссылки

LLM StatsArtificial Analysis