Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Task Generation on AZR
Loading...
19.95
Utility
PROPEL
4.6828
8.6464
12.61
16.5736
Jun 10, 2026
Utility
Validity
Self-BLEU-3
Distinct-3
Top-Topic Coverage
Updated 1mo ago
Evaluation Results
Method
Method
Links
Utility
Validity
Self-BLEU-3
Distinct-3
Top-Topic Coverage
PROPEL
Solver=3B
2026.06
19.95
90.85
80.9
26.6
73.5
PROPEL WCO
Solver=3B
2026.06
17.25
83.46
71.4
36
68.5
PROPEL
Solver=7B
2026.06
12.55
88.28
73.4
34.6
67.4
Base
Solver=3B
2026.06
10.09
66.54
71.1
37.6
31.8
PROPEL WCO
Solver=7B
2026.06
9.81
84.57
70
37.7
53.5
Base
Solver=7B
2026.06
5.27
67.48
72
36.9
29.3
Feedback
Search any
task
Search any
task