DROP Benchmark

Explore score history ↗

DROP is an AI benchmark in the Benchmark Radar catalog.

Released: 2019-03-04
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

DROP results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Claude 3.5 Sonnet	—	87.1	—	evidence
DeepSeek-V3	—	91.6	—	evidence
GPT-4 Turbo	—	86.0	—	evidence
Kimi k2 instruct	—	93.5	—	evidence
Nova Pro	—	85.4	—	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 DROP?

DROP