Mathematics
FrontierOR
FrontierOR asks models to read an operations research problem stated in plain language and write an optimization program, then checks how many large instances that program solves feasibly against an expert verified reference.
179items
7subjects
cc-by-4.0license
reasoningdomain
software_engineeringdomain
mathematicsdomain
textmodality
item-level responses released
Saturation status: No
Response matrix
Loading session strips…
lowhighUnobserved
Scale: {0, 0.2, 0.4, 0.6, 0.8, 1.0}