#56
Grok 3 Mini
grok-3-mini
0.0
Helpfulness
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 82 tok/s
Release Date
February 19, 2025
Lab
xAI
Type
Proprietary
Context Size
131.1K
Max Output Tokens
8.2K
Cost per 1 million tokens
$0.30 / $0.50
Model Inputs*
Text, Images, Code, Web
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
78.26 pts
Rank #56
19th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Grok 3 Mini is a smaller, more cost-efficient variant of Grok 3 that keeps much of its strong reasoning and math performance while targeting lower latency and price. It works well for high-volume tasks like classification, summarization, routing, and STEM question answering where fast responses matter more than absolute peak quality. The model remains a generally helpful and emotionally aware assistant, but its creative writing and deep comprehension lag behind larger frontier-scale systems, especially on long, open-ended projects.

Overall Score vs Price

Price axis is logarithmic (USD per 1M input tokens) · Higher score and lower price is better

Ringed point is this model

Anthropic
DeepSeek
Google
Meta
Moonshot
OpenAI
SpaceX AI
Zhipu AI

Intelligence

Overall Score · Higher is better

Speed

Output tokens per second · Higher is better

Price

USD per 1M input tokens · Lower is better

SpaceX AI Models

Overall Score · Same provider

Grok Family

Overall Score · Same model family

Closest Rivals

Overall Score · Nearest by overall rank