GPT-5 Mini
Parameters
100B (Estimated)
Context Length
400K
Modality
Text
Architecture
Undisclosed
License
Proprietary
Release Date
13 Nov 2025
Knowledge Cutoff
May 2024
API Pricing (per 1M)
Input: $0.25 · Output: $2.00
Evaluation Benchmarks
Rank
#51
| Benchmark | Score | Rank |
|---|---|---|
StackUnseen | 0.825 | 14 |
Software Engineering | 0.60 | 28 |
Graduate-Level QA | 0.823 | 57 |
Web Development | medium 1419 | 61 |
General Text | high 1390 | 103 |
Agentic Index | high 0.09 | 104 |
Intelligence Index | high 0.17 medium 0.21 low 0.10 | 144 126 189 |
Coding Index | high 0.16 | 137 |
Summarization Archived | 0.982 | 🥇 1 |
Rankings
Overall Rank
#51
Coding Rank
#47
About GPT-5 Mini
GPT-5 Mini is a lightweight, cost-effective reasoning model from OpenAI optimized for high-volume conversational and agentic workloads. It provides native multimodal support and adjustable thinking effort within an expanded context window.
Technical Specifications
Architecture specifications are undisclosed for proprietary models.
Attention
Attention Structure
Multi-Head Attention
Attention Heads
Undisclosed
Key-Value Heads
Undisclosed
Attention Head Dimension
Undisclosed
Position Embedding
Absolute Position Embedding
RoPE Theta
Undisclosed
Sliding Window Attention
Undisclosed
Sliding Window Size
Undisclosed
Sliding Window Ratio
Undisclosed
Linear Attention
Undisclosed
Linear Attention Ratio
Undisclosed
Normalization
Undisclosed
Activation Function
Undisclosed
Dimensions
Hidden Dimension Size
Undisclosed
Number of Layers
Undisclosed
FFN Intermediate Size (Dense)
Undisclosed
Multi-Token Prediction Heads
Undisclosed
Tokenizer
Vocabulary Size
Undisclosed
Resources
About GPT-5
OpenAI's latest generation of language models featuring advanced reasoning capabilities, extended context windows up to 400K tokens, and specialized variants for coding, general intelligence, and efficiency. GPT-5 series introduces improved thinking modes, superior performance across benchmarks, and variants optimized for different use cases from high-capacity Pro models to efficient Nano models. Features native multimodal understanding, enhanced mathematical reasoning, and state-of-the-art coding abilities through Codex variants.