| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Paraphrase Detection | MRPC | Empirical Error G(W)0.1 | 90 | |
| Paraphrase Detection | MRPC | Accuracy90.43 | 90 | |
| Paraphrase Detection | MRPC | Avg Accuracy89.9 | 89 | |
| Paraphrase Detection | MRPC | Accuracy76.2 | 68 | |
| Sentence Similarity | MRPC (test) | F1 (micro)78.36 | 44 | |
| Paraphrase Detection | MRPC GLUE (val) | Accuracy85.54 | 27 | |
| Semantic Similarity | MRPC (test) | Test Accuracy91.3 | 24 | |
| Paraphrase Detection | MRPC | Delta Accuracy0 | 24 | |
| Paraphrase Identification | MRPC | Delta 1-4.73 | 24 | |
| Natural Language Understanding | MRPC (test) | Accuracy89.46 | 14 | |
| Paraphrase Classification | MRPC | Utility Accuracy88 | 12 | |
| Paraphrase Detection | MRPC | Spearman Correlation (x100)30.87 | 12 | |
| Paraphrase Detection | MRPC Near OOD | Accuracy80.2 | 10 | |
| Binary Classification | MRPC (test) | Accuracy87.86 | 10 | |
| Ranking correlation with full dataset evaluation | MRPC | Kendall Correlation0.65 | 10 | |
| Classification | MRPC (test) | Macro F181.2 | 9 | |
| Pair Classification | MRPC | AP87.05 | 6 | |
| Semantic Paraphrase Detection | MRPC | MRPC Accuracy69.5 | 6 | |
| Paraphrase | NO-MRPC NLEBench (test) | Accuracy73.7 | 6 | |
| Classification | MRPC | Accuracy86.52 | 6 | |
| Paraphrase Detection | MRPC (val) | F1 Score93.8 | 6 | |
| Paraphrase Detection | MRPC (dev) | F1 Score91 | 6 | |
| Semantic Equivalence | MRPC | Success Rate70 | 5 | |
| Paraphrase Identification | MRPC | Accuracy76 | 5 | |
| Paraphrase Detection | MRPC GLUE (test) | F1 Score88 | 5 |