belfort 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 belfort.
Wer is the reported evaluation metric for belfort. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Lower is better
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | PyLaia (all transcriptions + agreement-based split) | verified | 15.14 | 2023 | Paper ↗ | Looks wrong? |
| 02 | PyLaia (rover consensus + agreement-based split) | verified | 17.08 | 2023 | Paper ↗ | Looks wrong? |
| 03 | PyLaia (human transcriptions + agreement-based split) | verified | 19.12 | 2023 | Paper ↗ | Looks wrong? |
| 04 | PyLaia (human transcriptions + random split) | verified | 28.11 | 2023 | Paper ↗ | Looks wrong? |
Cer is the reported evaluation metric for belfort. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Lower is better
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | PyLaia (all transcriptions + agreement-based split) | verified | 4.34 | 2023 | Paper ↗ | Looks wrong? |
| 02 | PyLaia (rover consensus + agreement-based split) | verified | 4.95 | 2023 | Paper ↗ | Looks wrong? |
| 03 | PyLaia (human transcriptions + agreement-based split) | verified | 5.57 | 2023 | Paper ↗ | Looks wrong? |
| 04 | PyLaia (human transcriptions + random split) | verified | 10.54 | 2023 | Paper ↗ | Looks wrong? |