BEA
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Grammatical Error Correction | BEA shared task 2019 (test) | F0.5 Score80.84 | 139 | |
| Grammatical Error Correction | BEA 2019 (test) | F0.575.9 | 47 | |
| Grammatical Error Correction | BEA 2019 (dev) | F0.5 Score63.4 | 19 | |
| Grammatical Error Correction | BEA (dev) | Precision (%)71.7 | 14 | |
| Grammatical Error Correction | BEA 19 | Precision74.7 | 12 | |
| Grammatical Error Correction | BEA (test) | Precision87.5 | 9 | |
| Grammatical Error Correction | BEA (val) | F0.548.72 | 8 | |
| Language Difficulty Prediction | BEA 2026 (test) | RMSE (ES)0.742 | 7 | |
| Lexical Difficulty Prediction | BEA Spanish Closed Track 2026 | RMSE0.903 | 4 | |
| Lexical difficulty prediction | BEA Chinese Closed Track 2026 | RMSE0.776 | 4 | |
| Lexical difficulty prediction | BEA German Closed Track 2026 | RMSE0.885 | 4 | |
| Grammatical Error Detection | BEA 2019 (dev) | F0.5 Score72.13 | 4 | |
| CTT-difficulty prediction | BEA (466/201 split) | Standard Deviation (SD)0.309 | 3 | |
| 2-Way Classification | BEA Shared Task 2 Track 4 (Unseen Questions) 2026 (Evaluation) | Quadratic Weighted Kappa0.49 | 3 | |
| CTT-difficulty prediction | BEA (pooled items) | Standard Deviation (SD)0.309 | 2 |
Showing 15 of 15 rows