OpenAI
GPT-5.2 Codex (xhigh)
GPT-5.2 Codex (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 Speed87.7 tok/s
First Token6.18s
Blended Price$4.81/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseDec 11, 2025
Context Windown/a
Modalitiesn/a
Strength: SciCode
Rank #6 across 472 models.
54.6%
Strength: GPQA
Rank #14 across 478 models.
89.9%
Strength: HLE
Rank #17 across 474 models.
33.5%
Watch Area: Output $
Rank #282 across 325 models.
$14.00/M
Watch Area: Blended $
Rank #280 across 325 models.
$4.81/M
Watch Area: TTFT
Rank #245 across 293 models.
6.18s
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 | 49.0 | #26 |
| Artificial Analysis Coding Index | coding | 43.0 | #34 |
| GPQA | reasoning | 89.9% | #14 |
| Humanity's Last Exam | reasoning | 33.5% | #17 |
| SciCode |