MBPP Benchmark

Explore score history ↗

MBPP is an AI benchmark in the Benchmark Radar catalog.

Released: 2021-08-17
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

MBPP results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Gemini 1.5 Pro 002	—	89.7	—	evidence
Llama-3.3 Nemotron Super 49B v1	—	91.3	—	evidence
O1 Mini	—	93.1	—	evidence
O1 Preview	—	95.5	—	evidence
Qwen2.5-Coder-32B-Instruct	—	90.5	—	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 MBPP?

MBPP