SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects

SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects is an AI benchmark in the Benchmark Radar catalog.

Released: 2023-09-15
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Glot-500	—	64.2	—	evidence
GPT-3.5-Turbo	—	43.3	—	evidence
MLP	—	62.8	—	evidence
XLM-R	—	75.9	—	evidence
XLM-R	—	71.0	—	evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects?