MLS-Bench
MLS-Bench Lite
A 30-task subset of MLS-Bench that evaluates whether AI systems can invent generalizable and scalable machine-learning methods.
ModelsModels with a result.4
Top resultBest result on this test.N/A
Top-3 spreadPoints from first to third.N/A
YearYear of release.2026
Results
4 results#ModelResultThe score from the source.
