TAU2
Measured May 29, 2026Source
Score
0.23
Models9 0 
GPT-5.4 mini (Non-Reasoning)
OpenAIOpenAIUnited States
A smaller, non-reasoning variant of the GPT-5.4 model from OpenAI. It is optimized for fast, low-cost responses in tasks that do not require complex chain-of-thought or deep reasoning capabilities.
CodingFastCheap
Input / 1M tokens
$0.75Output / 1M tokens
$4.50Output tokens/s
156.8First-token seconds
0.49sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 29, 2026Source
Score
0.18
Lcr
Measured May 29, 2026Source
Score
0.3
Ifbench
Measured May 29, 2026Source
Score
0.39
Scicode
Measured May 29, 2026Source
Score
0.4
Hle
Measured May 29, 2026Source
Score
0.06
Gpqa
Measured May 29, 2026Source
Score
0.61
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
25.3
Artificial Analysis Intelligence Index
Measured May 29, 2026Source
Score
23.3
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server