Model

Gemini 4 Argon

Google

deepmind.google

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CritPt27.1accuracyN/AIndependentlowepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
SciCode61.8scoreN/AIndependentmediumartificialanalysis.ai

Reproduced by the community

Loading community runs…