Guides
Every Modeldle question is built on a real number: a price, a context window, a release date or an LMArena score. These short guides explain what those numbers mean, where they come from and how to compare them, with examples from the models in the quiz. To test yourself, play the daily AI quiz or work through our AI trivia questions.
- 5 min read
What is a context window?
How much text an AI model can read at once, how tokens relate to words, why replies have their own limit, and what huge context windows can and cannot do.
- 5 min read
How AI token pricing works
Why AI models charge per million tokens, why output costs more than input, a worked cost example with real prices, and how caching and batch discounts change the bill.
- 5 min read
What is LMArena and how does it rank models?
How LMArena, formerly Chatbot Arena, turns anonymous head-to-head votes into model scores, how to read the gaps and ties, and what the rankings cannot tell you.
- 4 min read
Open weights vs closed AI models
What open weights really means, how it differs from open source, and the trade-offs between models you can download and models you can only use through an API.
- 5 min read
What do AI model parameters mean?
What the B in 70B means, total vs active parameters in mixture of experts models, why bigger is not always better, and why many labs keep model sizes secret.
- 4 min read
Knowledge cutoffs explained
Why AI models only know the world up to a certain date, why that date lands months before release, and how web search and other tools work around it.
Put it to the test
Eight quick questions, a new deck every day, and a source behind every answer.