Model

Gemini Ultra

Google

deepmind.google

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
MMLU83.7average_(%)N/AIndependentmediumpaperswithcode.com

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
MATH53.2accuracyN/AIndependentmediumarxiv.org

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
ChartQA80.81:1_accuracyN/AIndependentmediumarxiv.org
NExT-QA29.9wupsN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…