GPT-5.1 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-5.1 High
High-capability GPT-5.1 model with enhanced reasoning and broad domain expertise. Strong performer across web development (Elo 1393), coding (72.49), mathematics (86.90), and reasoning (78.79). Features improved thinking mechanisms and comprehensive language understanding. Balanced performance across all LiveBench categories with particular strength in mathematical reasoning.
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
#10
| Benchmark | Score | Rank |
|---|---|---|
Coding Aider Coding | 0.88 | 🥇 1 |
Agentic Coding LiveBench Agentic | 0.53 | ⭐ 4 |
Mathematics LiveBench Mathematics | 0.87 | ⭐ 5 |
Reasoning LiveBench Reasoning | 0.79 | ⭐ 9 |
StackUnseen ProLLM Stack Unseen | 0.84 | 9 |
Data Analysis LiveBench Data Analysis | 0.72 | 11 |
Web Development WebDev Arena | 1393 | 12 |
Coding LiveBench Coding | 0.72 | 26 |
Graduate-Level QA GPQA | 0.88 | 31 |
Rankings
Overall Rank
#10
Coding Rank
#10