GPT-5.4 mini
Parameters
-
Context Length
400K
Modality
Multimodal
Architecture
Dense
License
Proprietary
Release Date
17 Mar 2026
Knowledge Cutoff
-
Evaluation Benchmarks
| Benchmark | Score | Rank |
|---|---|---|
Data Analysis high | 0.71 | 31 |
Data Analysis max | 0.71 | 31 |
Mathematics high | 0.78 | 33 |
General high | 0.66 | 34 |
Reasoning high | 0.71 | 35 |
Coding high | 0.72 | 36 |
Coding max | 0.72 | 36 |
Agentic Coding high | 0.42 | 38 |
Agentic Coding max | 0.42 | 38 |
LiveBench Average high | 0.66 | 42 |
LiveBench Average max | 0.66 | 42 |
General Text high | 1448 | 51 |
Web Development high | 1397 | 56 |
Rankings
Overall Rank
-
Coding Rank
-
About GPT-5.4 mini
GPT-5.4 mini is OpenAI's fast, efficient small model that brings many capabilities of GPT-5.4 to high-volume workloads. It significantly improves over GPT-5 mini across coding, reasoning, multimodal understanding, and tool use while running more than 2x faster. Approaches GPT-5.4 performance on SWE-Bench Pro (54.4%) and OSWorld-Verified (72.1%). Supports text and image inputs, tool use, function calling, web search, file search, computer use, and skills. 400K context window. Pricing: $0.75/M input, $4.50/M output. Available via API as gpt-5.4-mini. Released March 17, 2026.
Technical Specifications
Detailed architecture specifications are limited for proprietary models.
Resources
About GPT-5.4
GPT-5.4 is OpenAI's most capable and efficient frontier model for professional work, combining the industry-leading coding capabilities of GPT-5.3-Codex with major advances in reasoning, computer use, and agentic workflows. It introduces native computer-use capabilities, tool search for large tool ecosystems, substantially improved knowledge work (spreadsheets, presentations, documents), and is OpenAI's most factual and token-efficient reasoning model. Supports up to 1M context tokens in Codex. Released March 5, 2026.