o4-mini
Parameters
-
Context Length
128K
Modality
Text
Architecture
Dense
License
Proprietary
Release Date
10 Feb 2026
Knowledge Cutoff
-
Technical Specifications
Attention Structure
Multi-Head Attention
Hidden Dimension Size
-
Number of Layers
-
Attention Heads
-
Key-Value Heads
-
Activation Function
-
Normalization
-
Position Embedding
Absolute Position Embedding
o4-mini
o4-mini brings efficient reasoning capabilities to cost-sensitive applications. More compact than o3 series while maintaining solid performance on reasoning tasks. Offers excellent balance of reasoning capability and cost-effectiveness, making deliberative AI accessible for broader use cases. Performs well on mathematics, coding challenges, and structured problem-solving. Ideal for applications requiring thoughtful analysis at scale.
About o4
The o4-mini series brings efficient reasoning capabilities to smaller form factors, making advanced deliberative AI more accessible. Optimized for cost-effective deployment while maintaining strong performance on reasoning benchmarks, ideal for applications requiring thoughtful analysis at scale.
Other o4 Models
- No related models available
Evaluation Benchmarks
Rank
#42
| Benchmark | Score | Rank |
|---|---|---|
Coding Aider Coding | 0.72 | 8 |
Graduate-Level QA GPQA | 0.81 | 20 |
Professional Knowledge MMLU Pro | 0.81 | 29 |
Rankings
Overall Rank
#42
Coding Rank
#35