DiG-bench: 70 hidden-rule games that test autonomous discovery, not just reasoning
DiG-bench is a benchmark of scientific discovery built as 70 text-based games, each with transformation rules an agent must uncover purely through interaction and experimentation. Twenty-one games are public; the rest stay private for secure evaluation, and every game has been beaten by at least one human on a first attempt. The point: these tests isolate a prerequisite for creativity — autonomously finding useful, undocumented truths about genuinely novel setups. Early results suggest some frontier models already approach human performance.