Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

M2D2

Benchmarks

Task NameDataset NameSOTA ResultTrend
Causal Language ModelingM2D2 (test)
Accuracy (Coding)100
11
Language Modelingm2d2 s2orc (val)
Perplexity21.803
2
Showing 2 of 2 rows