Belebele Benchmark

Explore score history ↗

Belebele is an AI benchmark in the Benchmark Radar catalog.

Released: 2024-07-25
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

Belebele results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
cogito-v1-preview-qwen-14B	—	88.4	—	evidence
GaMS3-12B-Instruct,bos	—	86.29	—	evidence
gemma-2-9b-it	—	87.31	—	evidence
gemma-3-12b-it,bos	—	88.2	—	evidence
Qwen3-14B	—	87.39	—	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 Belebele?

Belebele