Tokenization on AI4Bharat Sangraha Bengali
1,638Token Count (M)BrahmicTokenizer-131K
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BrahmicTokenizer-131KEvaluation Protocol=27M-document Indic pretraining corpus2026.05 | 1,638 | — | |
| Sarvam-1Evaluation Protocol=27M-document Indic pretraining corpus2026.05 | 1,524 | -6.9 | |
| Sarvam-30BEvaluation Protocol=27M-document Indic pretraining corpus2026.05 | 1,282 | -21.7 | |
| Tekken/SmEvaluation Protocol=27M-document Indic pretraining corpus2026.05 | — | 20.5 |