ML Engineering
MLR-Bench
Released idea-generation and research-proposal reviews for 201 ML research tasks, six generator models and two LLM reviewers. Each observation is one rubric dimension of a released review.
5,226items
6subjects
MITlicense
ml_engineeringdomain
reasoningdomain
textmodality
item-level responses released
Saturation status: No
Response matrix
Loading response matrix…
lowhighUnobserved
Scale: Grades: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10