Benchmark

MBPP EvalPlus

MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers…

Modality
text
Categories
reasoning, general
Openness
unknown
Source
llm_stats
Reported scores
2

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Llama 3.1 405B InstructMeta0.8862024-07-23evidence
Llama 3.3 70B InstructMeta0.8762024-12-06evidence

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.