Text Classification on IMDB (test) (Calibration & Uncertainty Metrics)
0.9447AccuracyRoBERTa
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| RoBERTaEvaluation Protocol=Standalone (module validity)2026.03 | 0.9447 | — | — | — | 0.0154 | — | — | — | 0.1706 | 0.9238 | |
| L0GMEvaluation Protocol=Standalone (module validity)2026.03 | 0.9438 | — | — | — | 0.0127 | — | — | — | 0.1586 | 0.9316 | |
| DeBERTa-v3Evaluation Protocol=Standalone (module validity)2026.03 | 0.9416 | — | — | — | 0.0165 | — | — | — | 0.1767 | 0.9194 | |
| BERTEvaluation Protocol=Standalone (module validity)2026.03 | 0.9285 | — | — | — | 0.0184 | — | — | — | 0.1986 | 0.9072 | |
| DistilBERTEvaluation Protocol=Standalone (module validity)2026.03 | 0.9123 | — | — | — | 0.0207 | — | — | — | 0.2245 | 0.8896 | |
| TransformerEvaluation Protocol=Standalone (module validity)2026.03 | 0.9086 | — | — | — | 0.0216 | — | — | — | 0.2387 | 0.8843 | |
| L2E2024.08 | 0.873 | — | — | — | — | 0.301 | — | — | — | — | |
| DIRECTOR2026.02 | 0.8713 | 0.0407 | 0.8155 | 0.7335 | 0.0316 | 3.24 | 0.1931 | — | — | — | |
| HMC2024.08 | 0.868 | — | — | — | — | 0.308 | — | — | — | — | |
| DE2024.08 | 0.867 | — | — | — | — | 0.386 | — | — | — | — | |
| MCD2026.02 | 0.8596 | 0.044 | 0.814 | 0.7479 | 0.0418 | 3.47 | 0.2072 | — | — | — | |
| KEP2026.02 | 0.8576 | 0.0454 | 0.8102 | 0.7487 | 0.0551 | 3.79 | 0.2162 | — | — | — | |
| SV-DKL2026.02 | 0.8569 | 0.0558 | 0.7854 | 0.7532 | 0.0852 | 4.49 | 0.231 | — | — | — | |
| TS2026.02 | 0.8559 | 0.0473 | 0.8075 | 0.7545 | 0.0291 | 3.41 | 0.2104 | — | — | — | |
| KFLLA2026.02 | 0.8559 | 0.0471 | 0.8082 | 0.7545 | 0.0584 | 6.93 | 0.2186 | — | — | — | |
| Transformer2026.02 | 0.8559 | 0.0473 | 0.8075 | 0.7545 | 0.0696 | 3.95 | 0.2228 | — | — | — | |
| SGPA2026.02 | 0.8539 | 0.0496 | 0.8004 | 0.7644 | 0.0604 | 3.96 | 0.2219 | — | — | — | |
| CSGMCMC2024.08 | 0.848 | — | — | — | — | 0.401 | — | — | — | — | |
| Meta-SGMCMC2024.08 | 0.82 | — | — | — | — | 0.401 | — | — | — | — |