OpenAI
GPT-5.4 mini (Non-Reasoning)
GPT-5.4 mini (Non-Reasoning) is an OpenAI GPT-5 family model, positioned around stronger reasoning, coding, factuality, and agentic work than earlier GPT generations. This profile keeps the release context separate from the local Artificial Analysis measurements so you can compare the specific reasoning tier on benchmark quality, speed, and cost.
Introducing GPT-5Model Snapshot
ReleaseMar 17, 2026
Overall
Rank #292 across 526
16.6
Coding
Rank #166 across 436
25.3
Blended Price
Rank #242 across 357
$1.69/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 Speed165.1 tok/s
First Token0.53s
Max Outputn/a
Pricing
Blended$1.69/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 16.6 | #292 |
| Artificial Analysis Coding Index | coding | 25.3 | #166 |
| GPQA | reasoning | 60.6% | #291 |
| Humanity's Last Exam | reasoning | 5.7% | #272 |
| SciCode |