Passer au contenu principal
AITier

GPT-5.6 Sol (max)

OpenAIGPTProprietary

Description

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.

Date de sortie
2026-07-09
Paramètres
—
Longueur du contexte
1.1M
Modalités
image, pdf, text

Radar de capacités

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

Classements

Domaine#RangScoreSource
Capacité agentique2
80.0
LS
Classement codage1
98.0
AA
Classement général12
91.0
AA
Classement multimodal10
66.0
LS
Science5
94.0
AA

Scores de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

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

Code

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

General

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

Healthcare

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

Long Context

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

Math

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

Multimodal

OSWorld 2.062.6%Aut.

Reasoning

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

Vision

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

Indices d'évaluation 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

Scores par catégorie 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

Tarification

Prix d'entrée$5 / 1M tokens
Prix de sortie$30 / 1M tokens
Prix mixte (3:1)$11.25 / 1M tokens
Prix de lecture cache$0.5 / 1M tokens
Prix d'écriture cache$6.25 / 1M tokens

Vitesse

Tokens/sec78.3
Délai du premier token76.98s
Temps de réponse76.98s

Classement des Prix par Fournisseur

Classement des Prix par Fournisseur

2 fournisseurs

Moins cher: OpenAIPlus cher: Neon
FournisseurEntréeSortie
1OpenAIMoins cher
$0.00001
$0.00003
2Neon
$5
$30

Comparer les prix entre différents fournisseurs API pour ce modèle.

Sources externes

LLM StatsArtificial Analysis