OpenAI model product
5, designed for the hardest questions and highest-accuracy work.
Updated Aug 12, 2026. Default version: GPT-5.5 Pro
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for GPT-5.5 Pro.
| GeneBench | 33.2% | 01 | 2 | 100.0% | C | |
| GDPval-MM | 82.3% | 02 | 3 | 50.0% | C | |
| BrowseComp | 90.1% | 04 | 58 | 94.7% | C | |
| FrontierMath | 39.6% | 06 | 17 | 68.8% | C | |
| Humanity's Last Exam | 57.2% | 08 | 93 | 92.4% | C |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Provider-specific output speed and catalog latency for GPT-5.5 Pro. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Official vendor API pricing appears first, followed by individual provider offers.
| Poe | openai/gpt-5.5-pro | global | $27.27 | $163.64 | 400K | |
| Impossibl | openai/gpt-5.5-pro | global | $30 | $180 | 1.1M | |
| CrossModel | openai/gpt-5.5-pro | global | $30 | $180 | 1.1M | |
| FastRouter | openai/gpt-5.5-pro | global | $30 | $180 | 1.1M | |
| LLM Gateway | gpt-5.5-pro | global | $30 | $180 | 1.1M | |
| OpenCode Zen | gpt-5.5-pro | global | $30 | $180 | 1.1M | |
| Neon | gpt-5-5-pro | global | $30 | $180 | 1.1M | |
| ZenMux | openai/gpt-5.5-pro | global | $30 | $180 | 1.1M | |
| OrcaRouter | openai/gpt-5.5-pro | global | $30 | $180 | 1.1M | |
| Kilo Gateway | openai/gpt-5.5-pro | global | $30 | $180 | 1.1M | |
| Vercel AI Gateway | openai/gpt-5.5-pro | global | $30 | $180 | 1M | |
| OpenRouter | openai/gpt-5.5-pro | global | $30 | $180 | 1.1M | |
| OpenAI | gpt-5.5-pro | global | $30 | $180 | 1.1M | |
| Venice AI | openai-gpt-55-pro | global | $37.5 | $225 | 1M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| GPT-5.5 Pro | 75.8 | N/A | 1.1M | 128K | No | Proprietary |
Key information about GPT-5.5-Pro and its available data.
5, designed for the hardest questions and highest-accuracy work. 5 with significantly more comprehensive, well-structured, and accurate responses, with especially strong performance in business, legal, education, science, and data analysis. Priced at $30/1M input and $180/1M output tokens with a 1M context window.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about GPT-5.5-Pro.
GPT-5.5-Pro's default version was released on Apr 23, 2026.
GPT-5.5-Pro's official API price is $30 per million input tokens and $180 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $27.27 input and $163.64 output via Poe.
GPT-5.5-Pro was created by OpenAI.
The default version has a 1.1M token context window.
No. The default version is not marked as having publicly available weights.
14 provider offerings are linked to the default version.
Nearby ranked alternatives include Gemini 3.1 Pro, GPT-5.4, GPT-5.6-Luna.