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

Mathematical expression

Benchmarks

Task NameDataset NameSOTA ResultTrend
Language ModellingMathematical expression EVAL (test)
Exact Match100
19
Language ModellingMathematical expression VAR-SWAP (test)
Exact Match0
7
Language ModellingMathematical expression EASY (test)
Exact Match90
4
Language ModellingMathematical expression LEN (test)
Exact Match14
3
Language ModellingMathematical expression EQ-CONV (test)
Exact Match0
3
Showing 5 of 5 rows