GPT-5.4 is OpenAI's latest frontier model for professional work with stronger reasoning, coding, and tool use.
Added Mar 5, 2026
Context Window
922.0K
Max Output
128.0K
Input Price
$2.50/1M
Output Price
$15.00/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
35.4
Coding Index
41.0
Agentic Index
39.1
GPQA Diamond
Graduate-level scientific reasoning
74.8%
Better than 68% of models compared
HLE
Humanity's Last Exam
10.6%
Better than 71% of models compared
IFBench
Instruction-following benchmark
48.4%
Better than 62% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
35.1%
Better than 49% of models compared
AA-LCR
Long context reasoning evaluation
47.3%
Better than 63% of models compared
GDPval-AA
Economically valuable tasks
42.1%
Better than 89% of models compared
CritPt
Research-level physics reasoning
0.6%
Better than 71% of models compared
SciCode
Python programming for scientific computing
47.1%
Better than 95% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
37.9%
Better than 89% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
36.7%
Better than 90% of models compared
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
83.2%
Better than 50% of models compared
Last updated May 11, 2026
Artificial Analysis