OpenAI
GPT-5.4 nano (xhigh)
GPT-5.4 nano (xhigh) 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-5Operational Metrics
Output Speed160.3 tok/s
First Token3.88s
Blended Price$0.463/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseMar 17, 2026
Context Windown/a
Modalitiesn/a
Strength: SciCode
Rank #30 across 472 models.
46.9%
Strength: Coding
Rank #30 across 410 models.
43.9
Strength: HLE
Rank #39 across 474 models.
26.5%
Watch Area: TTFT
Rank #235 across 293 models.
3.88s
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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 44.0 | #46 |
| Artificial Analysis Coding Index | coding | 43.9 | #30 |
| GPQA | reasoning | 81.7% | #87 |
| Humanity's Last Exam | reasoning | 26.5% | #39 |
| SciCode |