Model

Inflection-1

Inflection AI

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ89.7scoreN/AIndependentmediumarxiv.org
LAMBADA78.5scoreN/AIndependentmediumarxiv.org
MMLU72.7exact_matchN/ASelf-reportedmediuminflection.ai
PIQA84.2scoreN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…