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

CaLM

Benchmarks

Task NameDataset NameSOTA ResultTrend
Causal ReasoningCaLM
Accuracy73.9
14
Causal InferenceCaLM (test)
ATE0.99
12
Causal ReasoningCaLM Mathematical
Accuracy93.5
3
Showing 3 of 3 rows