GPT 5.5
GPT-5.5 is an OpenAI model, built for agentic coding, computer use, and professional knowledge work with stronger reasoning and token efficiency.
- Reasoning
- Vision
- Native PDF input
- Tool Calling
- Structured Output
Added Apr 23, 2026
Pricing
Auto routing · per 1M tokens- Input
- $5.00
- Output
- $30.00
- Cache read
- $0.50
Specifications
- Context window
- 1M
- Max output
- 128K
- Avg output (7d)
- 585 tokens
- Longer than 52% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
38.4
Coding Index
74.9
Agentic Index
36.4
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
47.3%
Better than 62% of models compared
Harvey LAB-AA
Legal agentic work criterion pass rate
86.3%
Better than 45% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
1137 Elo
Better than 59% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
1353 Elo
Better than 71% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
21.2%
Better than 75% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
84.3%
Better than 98% of models compared
MLCR-AA
Medical long-context reasoning
17.8%
Better than 60% of models compared
Reasoning
HLE
Humanity's Last Exam
45.8%
Better than 93% of models compared
IFBench
Instruction-following benchmark
75.9%
Better than 94% of models compared
CritPt
Research-level physics reasoning
27.1%
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
14.6%
Better than 70% of models compared
SciCode
Python programming for scientific computing
55.8%
Better than 81% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
58.0%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
89.0%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
93.5%
Better than 97% of models compared
Terminal-Bench Hard (legacy)
Agentic coding and terminal use
60.6%
Better than 98% of models compared
T²-Bench Telecom (legacy)
Conversational AI agents in dual-control scenarios
93.9%
Better than 91% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
84.3%
Better than 98% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
42.5%
Last updated Oct 14, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…