Arithmetical Puzzle
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Arithmetical Puzzle OOD-1000 1.0
0.1pass@1
3
Arithmetical Puzzle 1.0 (OOD-F)
0.1Pass@1
3
Arithmetical Puzzle 1.0 (OOD-N)
0.001Pass@1
3
Arithmetical Puzzle 1.0 (ID)
0.2Pass@1
3