TAU2
Measured May 14, 2026Source
Score
0.35
Models9 0 
GPT-5.4 nano (Non-Reasoning)
OpenAIOpenAIUnited States
A lightweight, non-reasoning variant of the GPT-5 series optimized for speed and cost-efficiency. Designed for straightforward tasks where rapid response and low latency are prioritized over complex chain-of-thought reasoning.
FastCheap
Input / 1M tokens
$0.20Output / 1M tokens
$1.25Output tokens/s
156.37First-token seconds
0.52sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.24
Lcr
Measured May 14, 2026Source
Score
0.25
Ifbench
Measured May 14, 2026Source
Score
0.33
Scicode
Measured May 14, 2026Source
Score
0.35
Hle
Measured May 14, 2026Source
Score
0.04
Gpqa
Measured May 14, 2026Source
Score
0.56
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
27.9
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
24.4
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