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

Pairwise Comparison Accuracy Refinement on Coding

63.92Original Accuracy

Logistic Regression

49.744853.424957.10560.7851Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
63.9257.23-6.6989
2026.06
63.9257.96-5.9689
2026.06
63.9261.82-2.189
2026.06
63.9256.34-7.5889
2026.06
63.9262.45-1.4789
2026.06
63.9267.23.28100.6
2026.06
63.5556.37-7.1885
2026.06
63.5559.33-4.2185
2026.06
63.5561.63-1.9285
2026.06
63.5546.87-16.6885
2026.06
63.5563.43-0.1285
2026.06
63.5567.173.6296.6
2026.06
63.2456.34-6.9189
2026.06
63.2459.22-4.0289
2026.06
63.2461.47-1.7789
2026.06
63.2454.55-8.789
2026.06
63.2463.03-0.2189
2026.06
63.2466.273.03102.2
2026.06
53.7353.990.27266
2026.06
53.7353.25-0.48266
2026.06
53.7356.72.98266
2026.06
53.7350.87-2.86266
2026.06
53.7355.742.01266
2026.06
53.7377.7424.02278.8
2026.06
50.2953.242.95247
2026.06
50.2954.123.83247
2026.06
50.2957.26.9247
2026.06
50.2950.890.6247
2026.06
50.2955.385.09247
2026.06
50.2972.9122.62261.8