bbc-xsum is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for bbc-xsum.
Rouge 1 is the reported evaluation metric for bbc-xsum. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | BigBird-Pegasus | verified | 47.12 | 2020 | Paper ↗Code ↗ | Looks wrong? |
Rouge L is the reported evaluation metric for bbc-xsum. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | BigBird-Pegasus | verified | 38.8 | 2020 | Paper ↗Code ↗ | Looks wrong? |
Rouge 2 is the reported evaluation metric for bbc-xsum. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | BigBird-Pegasus | verified | 24.05 | 2020 | Paper ↗Code ↗ | Looks wrong? |