OpenAI
GPT-5.5 (low)
GPT-5.5 (low) is an OpenAI GPT-5.5 profile in this benchmark snapshot, part of the newest GPT-5.5 generation described by OpenAI as its most capable model line for ChatGPT and Codex work. Use this page to compare its reasoning setting against sibling GPT-5.5 variants on intelligence, coding, speed, latency, and price.
Introducing GPT-5.5Operational Metrics
Output Speed56.8 tok/s
First Token1.89s
Blended Price$11.25/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseApr 23, 2026
Context Windown/a
Modalitiesn/a
Strength: GPQA
Rank #10 across 478 models.
91.0%
Strength: Coding
Rank #9 across 410 models.
52.1
Strength: SciCode
Rank #13 across 472 models.
51.6%
Watch Area: Output $
Rank #311 across 325 models.
$30.00/M
Watch Area: Blended $
Rank #310 across 325 models.
$11.25/M
Watch Area: Input $
Rank #310 across 325 models.
$5.00/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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 50.8 | #18 |
| Artificial Analysis Coding Index | coding | 52.1 | #9 |
| GPQA | reasoning | 91.0% | #10 |
| Humanity's Last Exam | reasoning | 31.0% | #22 |
| SciCode |