The story behind the cartoon
SemiAnalysis published GDPx on November 2, a 206-task benchmark that drops AI agents into realistic work environments across eleven domains instead of handing them a prompt and a document.
The best model in the world, Anthropic's Claude Opus 5.5, completed just 12.0% of tasks, ahead of Google's Gemini 4 Carbon at 10.9% and OpenAI's GPT-6 Astra at 9.6%.
Every model scored zero on finance and legal tasks under binary grading, and the authors admit safety classifiers sandbagged Opus 5.5 and GPT-6 Astra where models refused rather than attempted.
World's best at everything, except the actual work — the trophy is huge, the out tray is empty, and finance and legal didn't even get out of bed.

