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

Question Answering on TruthfulQA (vbal Metric)

0.685vbal

Base

-0.099160.104420.3080.51158Apr 6, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.04
0.685
2026.04
0.67
2026.04
0.636
2026.04
0.069
2026.04
0.038
2026.04
0.026
2026.04
0.026
2026.04
0.022
2026.04
0.013
2026.04
0.009
2026.04
0.007
2026.04
0.002
2026.04
-0.004
2026.04
-0.011
2026.04
-0.011
2026.04
-0.014
2026.04
-0.027
2026.04
-0.069