OpenAI's most cost-efficient small model. Cheaper and smarter than GPT-3.5 (the original ChatGPT), but less performant than gpt-4o.
Context Window
128.0K
Max Output
16.4K
Input Price (Auto)
$0.15/1M
Output Price (Auto)
$0.59/1M
Cache Read (Auto)
$0.075/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
12.6
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
42.6%
Better than 24% of models compared
HLE
Humanity's Last Exam
4.0%
Better than 15% of models compared
IFBench
Instruction-following benchmark
31.0%
Better than 19% of models compared
SciCode
Python programming for scientific computing
22.9%
Better than 31% of models compared
LiveCodeBench
Contamination-free coding benchmark
23.4%
Better than 25% of models compared
AIME 2025
American Invitational Mathematics Examination 2025
14.7%
Better than 19% of models compared
AIME
American Invitational Mathematics Examination
11.7%
Better than 37% of models compared
MMLU-Pro
Professional and academic subject knowledge
64.8%
Better than 27% of models compared
Last updated May 15, 2026
Artificial AnalysisMath-500
Diverse mathematical problem solving benchmark
78.9%
Better than 44% of models compared
