Natural Language Inference on SNLI (Statistical Measures)
83.05Correlation CoefficientBERTScore
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| BERTScore2026.05 | 83.05 | 79.34 | 3.71 | |
| MATCHArescaled to [0, 1]=true2026.05 | 71.14 | 1.24 | 34.95 | |
| SimCSErescaled to [0, 1]=true2026.05 | 69.47 | 33.43 | 18.03 | |
| EmbSimrescaled to [0, 1]=true2026.05 | 65.7 | 33.36 | 16.17 | |
| MAUVE2026.05 | 41.5 | 47.67 | -6.17 | |
| R1-F12026.05 | 41.34 | 28.58 | 12.76 | |
| RL-F12026.05 | 38.24 | 26.44 | 11.8 | |
| METEOR2026.05 | 30.08 | 20.78 | 9.3 | |
| R2-F12026.05 | 19.07 | 10.26 | 8.81 | |
| BLEURTrescaled to [0, 1]=true2026.05 | -64.06 | -99.63 | 17.79 |