You are invited to evaluate AI's philosophical capabilities.

PhilosophyBench is a Stanford University research study evaluating AI systems’ ability to write English-language philosophy.

We study whether AI can develop original philosophical ideas with clarity, depth and sophistication.

This research study has been approved by Stanford University’s Institutional Review Board (IRB). PhilosophyBench is advised by an international group of philosophers and computer scientists, including Ruth Chang, Ned Block, Nancy Cartwright, Joshua Cohen, Kit Fine, Ned Hall, Gideon Rosen, Jonathan Schaffer, Susan Wolf, Crispin Wright, Stephen Yablo, Linda Zagzebski, Michael Cheng, Isaac Robinson, Neil Band, Zachary Lang, Sebastian Thrun, Chris Re, and Michael Bernstein.

We will follow all privacy and confidentiality requirements of Stanford’s IRB, including the requirement that data is only used for the purposes of this study, which explicitly exclude training or providing study data to AI model developers (including Anthropic, OpenAI, Meta, Google Deepmind, Deepseek, xAI, Kimi, et al). The goal of this project is not to collect data to train or improve AI models, but rather to independently evaluate the extent that AIs can write philosophy through a statistically validated methodology.