GPT-5.5

Proprietary

Context

Benchmarks

About GPT-5.5

GPT-5.5 is an AI model developed by OpenAI, released in 2026, made available as a proprietary (API-only) model. GPT-5.5 is OpenAI's smartest and most intuitive-to-use model at release, with strong gains in agentic coding, computer u.

On this page you'll find GPT-5.5's full specifications, including a context window of 1M tokens, 7 benchmark results. Review provider pricing and benchmark scores below, or compare GPT-5.5 head-to-head with other AI models.

→ More models by OpenAI → AI benchmarks leaderboard

Links

Announcement ↗ Paper ↗ API docs ↗

Community

Would you run GPT-5.5 again?

No votes yet — be the first.

Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

GPT-5.5 benchmark scores▶

Compare on the benchmark table →

Benchmark	Category	Score	Variant
BrowseComp	agentic	59.7%	with-browsing
SWE-bench Verified	code	76%	agentic
MMLU-Pro	general	87.5%	no-tools
AIME 2025	math	93%	tools
ARC-AGI-2	reasoning	7.2%
GPQA Diamond	reasoning	88.4%	no-tools
Humanity's Last Exam	reasoning	28.4%	no-tools

More models like GPT-5.5

GPT-Realtime-Translate

Frequently asked questions

What is GPT-5.5? ▶

GPT-5.5 is OpenAI's smartest and most intuitive-to-use model at release, with strong gains in agentic coding, computer u It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created GPT-5.5? ▶

GPT-5.5 was developed by OpenAI and released in 2026.

Is GPT-5.5 open source or proprietary? ▶

GPT-5.5 is a proprietary model. It is accessed through an API rather than by downloading the weights.

What is GPT-5.5's context window? ▶

GPT-5.5 supports a context window of 1M tokens.

How much does GPT-5.5 cost? ▶

Pricing for GPT-5.5 depends on the provider. See the providers table on this page for the latest API rates.

How does GPT-5.5 perform on benchmarks? ▶

GPT-5.5 is benchmarked across 7 evaluations on GenAIList, including BrowseComp (59.7%). See the full benchmark table below and compare it with other models.