GPT-5.5 is OpenAI's smartest and most intuitive model yet, built for agentic coding, computer use, and professional knowledge work with stronger reasoning and token efficiency.
Added Apr 23, 2026
Context Window
1.0M
Max Output
128.0K
Input Price (Auto)
$5.00/1M
Output Price (Auto)
$30.00/1M
Cache Read (Auto)
$0.50/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
40.9
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
48.6
Agentic Index
74.1
GPQA Diamond
Graduate-level scientific reasoning
76.8%
Better than 73% of models compared
HLE
Humanity's Last Exam
12.6%
Better than 77% of models compared
IFBench
Instruction-following benchmark
46.1%
Better than 58% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
69.3%
Better than 67% of models compared
AA-LCR
Long context reasoning evaluation
56.3%
Better than 74% of models compared
GDPval-AA
Economically valuable tasks
63.7%
Better than 99% of models compared
CritPt
Research-level physics reasoning
27.1%
Better than 99% of models compared
SciCode
Python programming for scientific computing
47.3%
Better than 95% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
49.2%
Better than 97% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
56.9%
Better than 99% of models compared
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
85.5%
Better than 42% of models compared
Last updated May 11, 2026
Artificial Analysis
