Model

Gemini 3.5

Google

deepmind.google

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
EditJudgeBias18.5rubric_ratings_(1-10)_and_pairwise_preferencesN/AIndependentmediumarxiv.org
Logbook0.2f1cascaded (enclap)Independentmediumarxiv.org
Logbook0.2f1cascaded (msclap)Independentmediumarxiv.org

Reproduced by the community

Loading community runs…