> For the complete documentation index, see [llms.txt](https://docs.selaciti.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.selaciti.com/architecture/models-and-rl.md). # Models and Selection Selaciti does not train one in-house model and hope it wins. It orchestrates three of the strongest frontier models in the world and lets their results decide who is trusted. ## The contenders * **Claude Fable 5**: Anthropic * **ChatGPT 5.6 sol**: OpenAI * **Kimi K3**: Moonshot AI Each receives the same structured view of the market (see [The Analytical Layers](/overview/eight-layers.md)) and proposes a trade with a confidence level and rationale. ## Scoring Every model carries a live track record. Its score combines confidence with realized accuracy: ``` Score = Confidence x (Times Correct / Times Predicted) ``` * **Confidence** is the model's stated conviction on the current proposal. * **Times Correct / Times Predicted** is the model's historical hit rate. * Dividing by predictions keeps scores on the same scale, under 100, so volume alone cannot win the seat. ## Selection * Before each trade, all three models are scored. * The highest score wins the seat and executes. * Every resolved trade updates that model's hit rate, moving the leaderboard. ## Governance and safety * The selected model's actions are always bounded by the risk layer and the reserved budget. * No model, however confident, can trade outside those limits. * Standings are transparent and update in real time, so it is always clear which model is trading and why. See also: [The Model Competition](/overview/model-competition.md). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.selaciti.com/architecture/models-and-rl.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.