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

Question Answering on QuALITY (test)

39.25F1 Score

Z-tokens (w/o infer)

34.237235.538636.8438.1414Mar 26, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.03
39.25---
2026.03
39.04---
2026.03
38.48---
2026.03
37.33---
2026.03
34.68---
2026.03
34.43---
2022.09
-37.936.6-
2022.09
-40.638.6-
2022.09
-4642.1-
2022.09
-37.834-
2026.03
---48.8
2026.03
---45.9