Predicting the 2025 Arima Kinen: Predictions from 3 Major Foundation Models 30 Minutes Before the Race! ChatGPT vs Gemini vs Claude
Analysis
This article describes an experiment where three large language models (LLMs) – ChatGPT, Gemini, and Claude – were used to predict the outcome of the 2025 Arima Kinen horse race. The predictions were generated just 30 minutes before the race. The author's motivation was to enjoy the race without the time to analyze the paddock or consult racing newspapers. The article highlights the improved performance of these models in utilizing web search and existing knowledge, avoiding reliance on outdated information. The core of the article is the comparison of the predictions made by each AI model.
Key Takeaways
- •The article focuses on comparing predictions from three different LLMs for a specific event.
- •The models' ability to use web search and current knowledge is highlighted as a key improvement.
- •The experiment provides a real-world application of LLMs in a time-sensitive scenario.
“The author wanted to enjoy the Arima Kinen, but didn't have time to look at the paddock or racing newspapers, so they had AI models predict the outcome.”