GPT-5 Mini High
Parameters
-
Context Length
400K
Modality
Text
Architecture
Dense
License
Proprietary
Release Date
13 Nov 2025
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
GPT-5 Mini High
Compact yet highly capable GPT-5 variant offering excellent performance with improved efficiency. Strong results across web development (Elo 1398), coding (76.07), and mathematics (82.20). Delivers near-flagship performance at reduced computational cost. Ideal for applications requiring balance between capability and resource efficiency.
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.
Other GPT-5 Models
Evaluation Benchmarks
Rank
#4
| Benchmark | Score | Rank |
|---|---|---|
Summarization ProLLM Summarization | 0.98 | 🥇 1 |
Agentic Coding LiveBench Agentic | 0.65 | ⭐ 6 |
StackUnseen ProLLM Stack Unseen | 0.82 | 7 |
Coding LiveBench Coding | 0.76 | 10 |
Web Development WebDev Arena | 1398 | 10 |
Mathematics LiveBench Mathematics | 0.74 | 20 |
Reasoning LiveBench Reasoning | 0.68 | 21 |
Rankings
Overall Rank
#4
Coding Rank
#5