#22
o4-mini
o4-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 95 tok/s
Release Date
April 16, 2025
Lab
OpenAI
Type
Proprietary
Context Size
200K
Max Output Tokens
100K
Cost per 1 million tokens
$1.10 / $4.40
Model Inputs*
Text, Images
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
84.13 pts
Rank #22
56th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
OpenAI's o4-mini is a next-generation efficient reasoning model released in April 2025, designed to bring the advanced capabilities of the o4 class to latency-sensitive and cost-constrained applications. It significantly outperforms previous mini models in math, coding, and complex instruction following, achieving scores comparable to much larger frontier models. With a massive 200k context window and rapid output generation, it is the premier choice for high-volume agentic tasks and real-time reasoning.

Intelligence

Overall Score; Higher is better

Claude Haik…
Grok 4 Fast…
DeepSeek V3…
Gemini 3 Fl…
GPT-5 Mini
o4-mini
Grok 4 Fast
o1
DeepSeek V3…
DeepSeek V3…

Speed

Output Tokens per Second; Higher is better

GPT-5 Nano
Llama 3.3 8…
Llama 4 Sco…
Gemini 2.5 …
o4-mini
DeepSeek V3…
Llama 4 Mav…
GPT-5 Mini
Gemini 2.0 …
Claude Haik…

Price

USD per 1M Tokens; Lower is better

DeepSeek R1
GLM 4.6
GLM 4.7
GLM 5
Claude Haik…
o4-mini
o3-mini
GPT 5.1
GPT 5
GPT 5.2

openai Models

Overall Score; Same provider comparison

GPT 5.1
o3
GPT 5.2
GPT 5
ChatGPT 4o
GPT-5 Mini
o4-mini
o1
o3-mini
GPT-5 Nano

O-Series Family

Overall Score; Same model family comparison

o3
o4-mini
o1
o3-mini

Closest Rivals

Overall Score; Nearest by overall rank

Claude Haik…
Grok 4 Fast…
DeepSeek V3…
Gemini 3 Fl…
GPT-5 Mini
o4-mini
Grok 4 Fast
o1
DeepSeek V3…
DeepSeek V3…