Skip to main content

o4-mini (high)

OpenAIOpenAI o-seriesProprietary

Description

o4-mini is OpenAI's latest small o-series model, optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks. It is faster and more affordable than o3.

Release Date
2025-04-16
Parameters
Context Length
200K
Modalities
file, image, text

Capability Radar

46
general
49
coding
92
reasoning
55
scienceest.
60
agents
85
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agents & Tools70
52.0
LS
Code Ranking118
56.0
AA
General Ranking105
66.0
AA
Math Reasoning18
95.0
AA
Multimodal Ranking57
72.0
LS
Science76
66.0
AA

Benchmark Scores (LLM Stats)

Agents

BrowseComp51.5%SR

Biology

GPQA81.4%SR

Code

Aider-Polyglot68.9%SR
SWE-Bench Verified68.1%SR
Aider-Polyglot Edit58.2%SR

Communication

TAU-bench Retail71.8%SR
TAU-bench Airline49.2%SR
Multi-Challenge43.0%SR

General

MMMU81.6%SR

Math

AIME 202493.4%SR
AIME 202592.7%SR
MathVista84.3%SR
Humanity's Last Exam14.7%SR

Multimodal

CharXiv-R72.0%SR

AA Evaluation Indices

Math Index
90.7
Intelligence Index
33.1
Coding Index
25.6
Math 500
1.0
Aime
0.9
Aime 25
0.9
Livecodebench
0.9
Mmlu Pro
0.8
Gpqa
0.8
Ifbench
0.7
Tau2
0.6
Lcr
0.6
Scicode
0.5
Hle
0.2
Terminalbench Hard
0.2

LLM Stats Category Scores

Biology
80
Chemistry
80
Healthcare
80
Multimodal
80
Physics
80
Code
70
Frontend Development
70
General
70
Math
70
Reasoning
70
Tool Calling
60
Vision
60
Agents
50
Communication
50
Search
50

Pricing

Input Price$1.1 / 1M tokens
Output Price$4.4 / 1M tokens
Blended Price (3:1)$1.925 / 1M tokens

Speed

Tokens/sec129.4 tokens/s
Time to First Token29.37s
Time to Answer29.37s

Available Providers

(LS internal units)

No provider data available

External Sources