#29
Grok 4
grok-4-0709Helpfulness
Instruction
Following
Comprehension
Empathy
Creative
Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 70 tok/s
Release Date
July 9, 2025
Lab
xAI
Type
Proprietary
Context Size
256K
Max Output Tokens
8.2K
Cost per 1 million tokens
$3.00 / $15.00
Model Inputs*
Text, Images, Code, Web
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
80.75 pts
Rank #29
42th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Grok 4 is a large-scale language model from xAI built to combine strong reasoning with native tool use and real-time search. It was trained with extensive reinforcement learning to handle difficult analytical problems, long-context reading, and grounded research-style queries using a very large context window. The model offers solid general helpfulness, emotionally aware dialogue, and capable creative writing, though its quality and efficiency sit a bit behind the very latest frontier systems, making it a robust but more traditional choice for many applications.
Intelligence
Overall Score; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
xai Models
Overall Score; Same provider comparison
Grok Family
Overall Score; Same model family comparison
Closest Rivals
Overall Score; Nearest by overall rank