TAU2
Measured May 14, 2026Source
Score
0.37
Models9 0 
GPT-5.4 mini (medium)
OpenAIOpenAIUnited States
GPT-5.4 mini (medium) is a balanced, lightweight variant within the GPT-5 series, optimized for a strong combination of performance and cost-efficiency. It retains core reasoning and multimodal capabilities while offering faster response times and lower operational costs compared to larger models in the family.
CodingReasoningFastCheapMultimodal
Input / 1M tokens
$0.75Output / 1M tokens
$4.50Output tokens/s
172.06First-token seconds
4.35sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.34
Lcr
Measured May 14, 2026Source
Score
0.61
Ifbench
Measured May 14, 2026Source
Score
0.65
Scicode
Measured May 14, 2026Source
Score
0.44
Hle
Measured May 14, 2026Source
Score
0.17
Gpqa
Measured May 14, 2026Source
Score
0.82
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
37.5
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
37.7
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
Discussion
Thinking... Make sure you are connected to GitHub server