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

General Knowledge QA on CSQA

84.1Accuracy

Distillable

23.98839.59455.270.806Apr 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
84.184.791.4
2026.04
83.984.192
2026.04
83.783.990.7
2026.04
80.480.789.9
2026.04
79.278.189.2
2026.04
79.179.191.6
2026.04
78.678.995
2026.04
74.875.393.4
2026.04
74.474.888
2026.04
74.373.991.2
2026.04
7475.294.7
2026.04
7170.888.8
2026.04
70.87192
2026.04
70.771.291.8
2026.04
70.57191.5
2026.04
68.968.887.7
2026.04
27.628.645
2026.04
26.332.230.4