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

Text Classification on IMDB (test) (Calibration & Uncertainty Metrics)

0.9447Accuracy

RoBERTa

0.8502680.8747840.89930.923816Feb 9, 2026Feb 16, 2026Feb 24, 2026Mar 3, 2026Mar 11, 2026Mar 18, 2026Mar 26, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.03
0.9447---0.0154---0.17060.9238
2026.03
0.9438---0.0127---0.15860.9316
2026.03
0.9416---0.0165---0.17670.9194
2026.03
0.9285---0.0184---0.19860.9072
2026.03
0.9123---0.0207---0.22450.8896
2026.03
0.9086---0.0216---0.23870.8843
2026.02
0.87130.04070.81550.73350.03163.240.1931---
2026.02
0.85960.0440.8140.74790.04183.470.2072---
2026.02
0.85760.04540.81020.74870.05513.790.2162---
2026.02
0.85690.05580.78540.75320.08524.490.231---
2026.02
0.85590.04730.80750.75450.02913.410.2104---
2026.02
0.85590.04710.80820.75450.05846.930.2186---
2026.02
0.85590.04730.80750.75450.06963.950.2228---
2026.02
0.85390.04960.80040.76440.06043.960.2219---