Benchmark

FunctionalMATH

A functional variant of the MATH benchmark that tests language models' ability to generalize reasoning patterns across different problem instances…

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

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Gemini 1.5 FlashGoogle0.5362024-05-01evidence
Gemini 1.5 ProGoogle0.6462024-05-01evidence

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.