Tokka-Bench: Evaluating Tokenizers Across 100 Natural and 20 Programming Languages

arXiv 2610.08794v1•41163c35cb505c059e20efbdbf3129f4c1de661abe1ab29e1595dfdb8e3e09a0

Paper metadata

arXiv ID
2610.08794
Version
v1
Category
cs.AI, cs.CL
Authors
Ben Gubler
Publication date
2026-10-08T04:00:00Z
Source identifier
2610.08794v1
Public record ID
record:sha256:41163c35cb505c059e20efbdbf3129f4c1de661abe1ab29e1595dfdb8e3e09a0

Source license ↗

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.

Evidence and limitations

Source ID
arxiv_research
Record identifier
41163c35cb505c059e20efbdbf3129f4c1de661abe1ab29e1595dfdb8e3e09a0
Record type
Source metadata

This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.