Big Bench Hard (BBH)

Explore score history ↗

Big Bench Hard (BBH) is an AI benchmark in the Benchmark Radar catalog.

Released: 2022-10-18
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

Big Bench Hard (BBH) results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Claude 3.5 Sonnet	—	93.1	—	evidence
Gemini 1.5 Pro	—	89.2	—	evidence
Gemma 3 27B	—	87.6	—	evidence
Kimi K2	—	88.71	—	evidence
Qwen 3	—	88.87	—	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 Big Bench Hard (BBH)?