GPT-5.5: benchmarks, price and rank

Its headline results

The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.

• Remote Labor Index6.3%

  Real freelance projects that people were paid to do, from design and video to architecture, games and data work. The model gets the same brief and files the freelancer got and has to hand back finished work.

  8th of 17. Independent result from Epoch AI.

• APEX-Agents55.1%

  Long tasks written by investment banking analysts, management consultants and corporate lawyers from their own work, done across files and apps in a realistic work setup.

  25th of 56. Independent result from Epoch AI.

• BrowseComp84.4%

  Questions whose answers are hidden deep on the web and take many searches and pages to track down.

  14th of 56. The maker's own number, from OpenAI, via LLM Stats.

• MCP Atlas75.3%

  Multi-step tasks where the model has to pick and combine many real tools, connected through MCP, the standard way agents plug into apps and data.

  13th of 33. The maker's own number, from OpenAI, via LLM Stats.

• SWE-Bench Pro58.6%

  Long changes to real codebases in several languages, often across many files, including code from private and copyleft projects that models are unlikely to have seen.

  22nd of 50. The maker's own number, from OpenAI, via LLM Stats.

• Humanity's Last Exam52.2%

  About 2,500 questions written by experts in more than a hundred fields to be as hard as they could make them, many needing a diagram or image.

  16th of 74. The maker's own number, from OpenAI, via LLM Stats.

• Vending-Bench 2$7,524

  The model runs a simulated vending machine business for a year on its own: finding suppliers, ordering stock, setting prices and paying the daily fees.

  18th of 60. Independent result from Epoch AI.

• OSWorld-Verified78.7%

  Ordinary tasks on a real desktop computer using normal apps: a browser, a spreadsheet, an email client, a photo editor, the file manager.

  9th of 25. The maker's own number, from OpenAI, via LLM Stats.

• Toolathlon55.6%

  Long tasks across many real apps and their tools, such as email, calendars, spreadsheets, code repositories and online stores.

  12th of 37. The maker's own number, from OpenAI, via LLM Stats.

• DeepSWE 1.167%

  Software engineering tasks run in the same simple agent setup for every model.

  Independent result from LLM Stats.