GPT-5.2: 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 Index2.5%

  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.

  13th of 17. Independent result from Epoch AI.

• BrowseComp65.8%

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

  34th of 56. The maker's own number, from OpenAI, via LLM Stats.

• MCP Atlas60.6%

  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.

  28th of 33. The maker's own number, from OpenAI, via LLM Stats.

• Humanity's Last Exam27.8%

  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.

  Independent result from Epoch AI.

• Vending-Bench 2$3,591

  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.

  46th of 60. Independent result from Epoch AI.

• Toolathlon46.3%

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

  24th of 37. The maker's own number, from OpenAI, via LLM Stats.

• SimpleBench45.8%

  Multiple-choice puzzles about everyday situations, space, time and people, written to trip up models that pattern-match instead of think. Ordinary adults do well on them.

  59th of 68. Independent result from Epoch AI.

• SimpleQA Verified37.1%

  Short factual questions with one checked answer, asked without web search.

  51st of 78. Independent result from Epoch AI.

• FrontierMath67.4%

  Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.

  35th of 76. Independent result from Epoch AI.

• MMMU-Pro79.5%

  College exam questions that need a picture to answer, such as charts, diagrams, maps and chemical structures, with more answer options than the original MMMU and some questions shown only as a screenshot.

  16th of 51. The maker's own number, from OpenAI, via LLM Stats.