TAU2
Measured May 14, 2026Source
Score
0.7
Models9 0 
Grok 4.20 0309 (Non-reasoning)
xAIxAIUnited States
Grok 4.20 0309 (Non-reasoning) is a variant of the Grok model optimized for speed and efficiency, designed for tasks that do not require deep, step-by-step reasoning. It maintains strong multimodal capabilities and is suitable for rapid, high-volume interactions.
FastCheapMultimodal
Input / 1M tokens
$2.00Output / 1M tokens
$6.00Output tokens/s
76.74First-token seconds
0.64sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.22
Lcr
Measured May 14, 2026Source
Score
0.18
Ifbench
Measured May 14, 2026Source
Score
0.48
Scicode
Measured May 14, 2026Source
Score
0.32
Hle
Measured May 14, 2026Source
Score
0.23
Gpqa
Measured May 14, 2026Source
Score
0.79
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
25.4
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
29.7
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