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

Factuality Verification on Climate-Fever

78.91Correctness Score

BERTScore

-46.4724-13.921218.6351.1812May 26, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.05
78.9177.741.17-
2026.05
70.9551.9918.96-
2026.05
65.6351.826.91-
2026.05
60.5655.742.41-
2026.05
52.9212.5720.18-
2026.05
26.7823.053.73-
2026.05
19.6218.121.5-
2026.05
19.0115.333.68-
2026.05
7.555.671.88-
2026.05
-41.65-53.766.06-
2026.05
---37.11
2026.05
---34.07
2026.05
---34.48
2026.05
---36.93
2026.05
---33.33
2026.05
---33.33
2026.05
---40.23
2026.05
---33.33
2026.05
---64.08