List your company

Tokenization on AI4Bharat Sangraha Assamese

100Token Count (M)Sarvam-1
65.6874.5983.592.41May 28, 2026

Evaluation results

MethodLinks
Sarvam-1Evaluation Protocol=27M-document Indic pretraining corpus2026.0510049.6
Sarvam-30BEvaluation Protocol=27M-document Indic pretraining corpus2026.05681.9
BrahmicTokenizer-131KEvaluation Protocol=27M-document Indic pretraining corpus2026.0567—
Tekken/SmEvaluation Protocol=27M-document Indic pretraining corpus2026.05—49.4