LAMBADA Benchmark

Explore score history ↗

LAMBADA is an AI benchmark in the Benchmark Radar catalog.

Released: 2016-06-21
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

LAMBADA results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
GPT-3 175B	—	86.4	—	evidence
PaLM 2-L	—	86.9	—	evidence
PaLM 2-M	—	83.7	—	evidence
PaLM-540B	—	89.7	—	evidence
PaLM-540B	—	81.8	—	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 LAMBADA?

LAMBADA