OpenAI
GPT-5.4 (Non-reasoning)
GPT-5.4 is OpenAI's best general-purpose model, part of the GPT-5 flagship model family. It's their most intelligent model yet for both general and agentic tasks.
Introducing GPT-5Model Snapshot
TypeLanguage
ReleaseMar 5, 2026
Context1,050,000
Tagsreasoning, tool-use, vision, file-input
Overall
Rank #108 across 526
35.4
Coding
Rank #52 across 436
41.0
Blended Price
Rank #314 across 357
$5.63/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed59.3 tok/s
First Token0.68s
Max Output128,000
Pricing
Blended$5.63/M
Input$2.50/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 35.4 | #108 |
| Artificial Analysis Coding Index | coding | 41.0 | #52 |
| GPQA | reasoning | 74.8% | #176 |
| Humanity's Last Exam | reasoning | 10.6% | #158 |
| SciCode |