Shypd.aiThe largest open index of AI toolsCan LLMs Play the Game of Science? is a research & education tool that evaluates scientific reasoning in large language models. It uses the Eleusis card game to test LLMs' ability to formulate and validate scientific hypotheses.
Trending
About
Can LLMs Play the Game of Science? is a Hugging Face Space designed to benchmark the scientific reasoning capabilities of large language models. This interactive tool utilizes the Eleusis card game, a game of inductive reasoning, to assess how well LLMs can formulate and validate scientific hypotheses. Users can explore a dynamic chart that plots various LLM scores against their "boldness" or "recklessness" index within the Eleusis game context. The platform provides a unique way to gain insights into the scientific reasoning strengths and weaknesses of different AI models, making it a valuable resource for researchers and academics interested in AI evaluation and cognitive science.
Capabilities
Pricing & Plans
Likely Free
Free
FAQs
Trending
