Winogrande Benchmark

Explore score history ↗

Winogrande is an AI benchmark in the Benchmark Radar catalog.

Released: 2019-07-25
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

Winogrande results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Command R	—	85.4	—	evidence
GPT 4	—	87.5	—	evidence
KImi K2 - Base	—	85.32	—	evidence
Llama 3.1	—	84.5	—	evidence
Qwen2 72B Instruct	—	85.1	—	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 Winogrande?

Winogrande