Human or Not

Human or Not recreates a fast, anonymous conversational Turing test as a live multiplayer game. When you press play, the service matches you with a random partner: either another real player somewhere in the world or an AI bot. The identity is hidden while the round runs, and the main interaction is a text chat limited to two minutes. You can choose the subjects and questions, probe for personal experiences, ask about recent events, or simply have an ordinary conversation while looking for signs of scripted or machine-generated replies. When time expires, the game asks you to decide whether the partner was human or AI, then reveals the answer and records the outcome. Correct decisions contribute points and can support ranking on the global Play & Rank leaderboard. The bot side currently uses large language models identified in the FAQ as GPT-5, Claude, and Google Gemini Flash, while prompts and models may change as the project evolves. Optional registration adds an account layer: users can save statistics and chat history, keep Human Coins, and qualify for leaderboard visibility; the core round remains available without registration. The site also publishes educational articles about the Turing Test, AI behavior, and related concepts, plus occasional challenges such as winning streaks and merchandise promotions. This is an entertainment and research-oriented experiment, not an authentication service, professional AI detector, dating safety tool, or guarantee that any conversation is private. The comparison workflow is especially valuable when a single prompt can be sent to several models and the decision depends on output quality rather than brand reputation. Users can use the available categories to narrow evaluation to the kind of artifact they actually need, compare alternatives visually, and return to leaderboards when a new model or benchmark result becomes relevant. This makes the site both a practical discovery surface and an ongoing reference for generative AI evaluation. The comparison workflow is especially valuable when a single prompt can be sent to several models and the decision depends on output quality rather than brand reputation. Users can use the available categories to narrow evaluation to the kind of artifact they actually need, compare alternatives visually, and return to leaderboards when a new model or benchmark result becomes relevant. This makes the site both a practical discovery surface and an ongoing reference for generative AI evaluation.