DataLearner logo
OP

OpenAI o4 - mini

Scheduled retirement · 2026-10-23Reasoning modelo Minio4

OpenAI o4 - mini

Release date: 2025-04-16Updated: 2026-09-04Scheduled retirement: 2026-10-23Views: 1,376
Live demoGitHubHugging FaceCompare
Parameters
No data
Context length
200K
Multilingual
Supported
Reasoning ability
4/5

OpenAI o4 - mini is an AI model published by OpenAI, released on 2025-04-16, for Reasoning model, and 200K context length, with a 2719.00 score on CodeForces.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

OpenAI o4 - mini

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
200K tokens
Max output length
No data
Model type
Reasoning model
Modality (in / out)
Text, Image → Text
Release date
2025-04-16
Model file size
No data
MoE architecture
No
Total params / Active params
No data / Not applicable
Knowledge cutoff
No data
OpenAI o4 - mini

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
N/A
Hugging Face
N/A
Live demo
N/A
OpenAI o4 - mini

Official resources

Paper
DataLearnerAI blog
N/A
OpenAI o4 - mini

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$1.10/ 1M tokens$4.40/ 1M tokens
Image-$1.10/ 1M tokens

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

OpenAI o4 - mini

Benchmark Results

OpenAI o4 - mini currently shows benchmark results led by AIME 2024 (1 / 62, score 98.70), MMLU (2 / 124, score 93), AIME2025 (10 / 107, score 99.50). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

5 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Thinking Mode
93
2 / 124
MMLU Pro
Thinking Mode
80.60
59 / 134
ARC-AGI-1
Thinking Mode
58.70
63 / 92
HLE
Thinking Mode
14.28
161 / 197
HLE
Thinking ModeTools
17.70
149 / 197

General Evaluation

3 evaluations
Benchmark / mode
Score
Rank/total
75.25
171 / 274
77.78
160 / 274
GPQA Diamond
Thinking Mode
81.40
134 / 274

Coding and Software Engineer

4 evaluations
Benchmark / mode
Score
Rank/total
CodeForces
Thinking ModeTools
2719
7 / 21
SWE-bench Verified
Thinking Mode
68.10
70 / 116
WeirdML v2
HighTools
52.56
35 / 52
GSO
HighTools
3.60
20 / 21

Math and Reasoning

17 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Thinking Mode
92.70
31 / 107
AIME2025
Thinking ModeTools
99.50
10 / 107
AIME 2024
Thinking Mode
93.40
5 / 62
AIME 2024
Thinking ModeTools
98.70
1 / 62
16.14
55 / 58
28.77
45 / 58
36.14
38 / 58
9.70
29 / 60
19.30
18 / 60
17.20
21 / 60
11.40
12 / 16
11.40
12 / 19
IMO 2024
Thinking Mode
7.70
7 / 10
2.10
56 / 80
6.30
35 / 80
4.88
34 / 42
IMO 2025
Thinking Mode
3
7 / 9

Common Sense Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
38.70
70 / 94

Agent Level Benchmark

4 evaluations
Benchmark / mode
Score
Rank/total
76.51
15 / 22
72
13 / 59
τ²-Bench
Thinking ModeTools
56.90
32 / 44
τ²-Bench - Telecom
Thinking ModeTools
50.20
34 / 36

Multimodal Understanding

3 evaluations
Benchmark / mode
Score
Rank/total
64
15 / 20
64
15 / 20
VPCT
Medium
57.50
8 / 24

Long Context

1 evaluations
Benchmark / mode
Score
Rank/total
77.80
9 / 16
OpenAI o4 - mini

Publisher

OpenAI o4 - mini

Model Overview

OpenAI o4 - mini is an AI model published by OpenAI, released on 2025-04-16, for Reasoning model, and 200K context length, with a 2719.00 score on CodeForces.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code