Multilingual
SIB-200
Original topic-classification outputs in 205 languages, with recorded language-specific classifier runs and zero-shot LLM replies.
41,820items
3,341subjects
Source repository and released results: Apache-2.0. Dataset text: CC-BY-SA-4.0, as declared in the author Hugging Face dataset card.license
multilingualdomain
textmodality
item-level responses released
Saturation status: Yes
Response matrix
Loading response matrix…
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect