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

MIL

Benchmarks

Task NameDataset NameSOTA ResultTrend
Proof Optimization (Mixed)MIL aggregated (test)
Improvement27.31
4
Proof Optimization (Declarativity)MIL aggregated (test)
Improvement9.34
4
Proof Optimization (Length)MIL aggregated (test)
Improvement20.96
4
Proof length optimizationMIL
Improvement43.55
4
Neural Theorem ProvingMIL General Subset
Pass@1539.13
2
Neural Theorem ProvingMIL-C04
Pass@1545.45
2
Proof declarativity optimizationMIL
Improvement13.45
2
Showing 7 of 7 rows