AI - Paski.devGPT-5.5
OpenAI llmSuccessor to GPT-5.4 across ChatGPT, the API and Codex, with reported gains in agentic coding, knowledge work and scientific research evaluations.
overall ⌄
66.8
14 of 93 ranked
price · $/M tokens
5 / 30
in / out, as of 2026-07-25
to run it yourself ⌄
API only
no weights to run
Benchmarks
What its maker published, and what anyone else measured. Every figure links the document it came from.
| benchmark | published | measured |
|---|---|---|
| GPQA | 93.6 | — |
| SWE-bench Pro | 59.4 | — |
Cheaper, and at least as good
On a 1,000-in, 1,000-out call these cost less and rank no lower — a hard comparison to argue with, and a narrow one. Value covers what it misses.
| DeepSeek V4-Pro DeepSeek | $0.00130 | overall 68.3 |
| GLM-5.2 Z.ai | $0.00580 | overall 68.2 |
| Gemini 3.1 Pro Google | $0.0140 | overall 71.6 |
| GPT-5.2 OpenAI | $0.0158 | overall 73.7 |
| Claude Sonnet 5 Anthropic | $0.0180 | overall 73.0 |
Lineage
No recorded lineage — root or standalone model.
Metadata
| org | OpenAI |
| released | 2026-04-24 |
| license | proprietary |