OpenAI
GPT-5.3 Codex (xhigh)
GPT-5.3-Codex advances both the frontier coding performance of GPT‑5.2-Codex and the reasoning and professional knowledge capabilities of GPT‑5.2, together in one model, which is also 25% faster. This enables it to take on long-running tasks that involve research, tool use, and complex execution.
Introducing GPT-5Model Snapshot
TypeLanguage
ReleaseFeb 5, 2026
Context400,000
Tagsfile-input, implicit-caching, reasoning, tool-use
Overall
Rank #49 across 600
44.3
Coding
No rank
n/a
Blended Price
Rank #319 across 379
$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 Speed120.3 tok/s
First Token39.43s
Max Output128,000
Pricing
Blended$4.81/M
Input$1.75/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 44.3 | #49 |
| GPQA | reasoning | 91.5% | #24 |
| Humanity's Last Exam | reasoning | 39.9% | #24 |
| SciCode | coding, reasoning | 53.2% | #25 |
| Output Speed |