Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Task Generation on Math
Loading...
41.93
Utility Score
PROPEL
15.5868
22.4259
29.265
36.1041
Jun 10, 2026
Utility Score
Validity Rate
Self-BLEU-3
Distinct-3
Top Topic Coverage
Updated 1mo ago
Evaluation Results
Method
Method
Links
Utility Score
Validity Rate
Self-BLEU-3
Distinct-3
Top Topic Coverage
PROPEL
Solver=3B
2026.06
41.93
96.04
0.708
0.387
0.751
PROPEL
Solver=7B
2026.06
27.91
95.65
0.652
0.464
0.516
Base
Solver=3B
2026.06
24.74
96.63
0.631
0.505
0.605
Base
Solver=7B
2026.06
16.6
96.63
0.631
0.505
0.605
Feedback
Search any
task
Search any
task
