Skip to main content
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.

Release Date
2026-07-09
Parameters
—
Context Length
1.1M
Modalities
image, pdf, text

Capability Radar

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

Rankings

Domain#RankScoreSource
Agentic Capability2
80.0
LS
Code Ranking1
98.0
AA
General Ranking12
91.0
AA
Multimodal Ranking10
66.0
LS
Science5
94.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

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

Code

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

General

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

Healthcare

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

Long Context

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

Math

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

Multimodal

OSWorld 2.062.6%SR

Reasoning

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

Vision

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

AA Evaluation Indices

(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

LLM Stats Category Scores

(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

Pricing

Input Price$5 / 1M tokens
Output Price$30 / 1M tokens
Blended Price (3:1)$11.25 / 1M tokens
Cache Read Price$0.5 / 1M tokens
Cache Write Price$6.25 / 1M tokens

Speed

Tokens/sec78.3
Time to First Token76.98s
Time to Answer76.98s

Provider Price Ranking

Provider Price Ranking

2 providers

Cheapest: OpenAIMost Expensive: Neon
ProviderInputOutput
1OpenAICheapest
$0.00001
$0.00003
2Neon
$5
$30

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis