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

Language Generation on QASPER

15.35Accuracy

E2E Caprese

9.557211.061112.56514.0689May 8, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
15.35
2025.05
15.16
2025.05
14.43
2025.05
14.42
2025.05
14.35
2025.05
14.34
2025.05
14.21
2025.05
14.11
2025.05
13.88
2025.05
13.88
2025.05
13.75
2025.05
13.4
2025.05
12.63
2025.05
12.52
2025.05
12.45
2025.05
12.36
2025.05
12.35
2025.05
12.26
2025.05
12.26
2025.05
11.6
2025.05
11.36
2025.05
11.07
2025.05
11.05
2025.05
11.03
2025.05
10.96
2025.05
10.82
2025.05
10.75
2025.05
10.46
2025.05
10.14
2025.05
10.11
2025.05
10.02
2025.05
9.92
2025.05
9.91
2025.05
9.82
2025.05
9.78