ReuF2F
A Lean 4 benchmark of 244 open problems from undergraduate research for evaluating coding agents.
Software, research, and experiments.
Results must match every included tag and none of the excluded tags.
Click once to select, twice to exclude, three times to clear.
No tags match that search.
A Lean 4 benchmark of 244 open problems from undergraduate research for evaluating coding agents.
An app for couples, built by my partner Grace Tian and me.
No projects match these filters.