OpenAI
GPT-5.3 Codex (xhigh)
GPT-5.3 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-5Model Snapshot
ReleaseFeb 5, 2026
Overall
Rank #44 across 526
44.3
Coding
Rank #9 across 436
53.1
Blended Price
Rank #311 across 357
$4.81/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 Speed84.5 tok/s
First Token64.15s
Max Outputn/a
Pricing
Blended$4.81/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 44.3 | #44 |
| Artificial Analysis Coding Index | coding | 53.1 | #9 |
| GPQA | reasoning | 91.5% | #12 |
| Humanity's Last Exam | reasoning | 39.9% | #10 |
| SciCode |