Claude Fable 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 Index16.1%

  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.

  6th of 17. Independent result from Epoch AI.

• APEX-Agents63.6%

  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.

  17th of 56. Independent result from Epoch AI.

• Terminal-Bench 4.044.5%

  Hard jobs done in a real computer terminal: building and fixing software, setting up systems, and science and engineering problems.

  Independent result from LLM Stats.

• SWE-Bench Pro80%

  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.

  4th of 50. The maker's own number, from Anthropic, via LLM Stats.

• FrontierSWE47.0%

  Open-ended technical projects that take hours to tens of hours, from making systems faster to building large programs and applied machine learning research. Each run gets a 20-hour budget.

  9th of 21. Independent result from Epoch AI.

• Humanity's Last Exam64.5%

  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.

  3rd of 74. The maker's own number, from Anthropic, via LLM Stats.

• Vending-Bench 2$5,680

  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.

  27th of 60. Independent result from Epoch AI.

• OSWorld-Verified85%

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

  2nd of 25. The maker's own number, from Anthropic, via LLM Stats.

• DeepSWE 1.170%

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

  Independent result from LLM Stats.

• SimpleBench81.9%

  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.

  9th of 68. Independent result from Epoch AI.