Optimized for speed and ideal for applications requiring low latency. The fastest and most efficient GPT-5 variant.
Added Aug 7, 2025
Context Window
400.0K
Max Output
128.0K
Input Price (Auto)
$0.050/1M
Output Price (Auto)
$0.40/1M
Cache Read (Auto)
$0.0050/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
26.8
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
20.3
GPQA Diamond
Graduate-level scientific reasoning
67.6%
Better than 58% of models compared
HLE
Humanity's Last Exam
8.2%
Better than 66% of models compared
IFBench
Instruction-following benchmark
67.6%
Better than 85% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
36.5%
Better than 52% of models compared
AA-LCR
Long context reasoning evaluation
41.7%
Better than 60% of models compared
SciCode
Python programming for scientific computing
36.6%
Better than 71% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
12.1%
Better than 54% of models compared
AIME 2025
American Invitational Mathematics Examination 2025
83.7%
Better than 80% of models compared
MMLU-Pro
Professional and academic subject knowledge
78.0%
Better than 59% of models compared
Last updated May 15, 2026
Artificial AnalysisLiveCodeBench
Contamination-free coding benchmark
78.9%
Better than 91% of models compared
