Model

Gemma

Google

deepmind.google

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
VaccineStance37.8f1N/AIndependentmediumarxiv.org

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
AVSD-Scenes69.8avg.N/AIndependentmediumarxiv.org
VisAudit57.1recovery_rateN/AIndependentmediumarxiv.org

Safety & Alignment

Safety & Alignment
BenchmarkScoreMetricHarnessSourceConfidenceLink
rt-inod-jailbreaking91.0best-ofN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…