BBB-Martins
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Distributional disagreement (sym-KL) | BBB-Martins (id-test) | Delta Sym-KL-0.05 | 5 | |
| Top-K ranking stability | BBB-Martins id (test) | Jaccard Similarity65 | 3 |
Showing 2 of 2 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Distributional disagreement (sym-KL) | BBB-Martins (id-test) | Delta Sym-KL-0.05 | 5 | |
| Top-K ranking stability | BBB-Martins id (test) | Jaccard Similarity65 | 3 |