Model

DeepSeek-Coder-V2-Lite-Base

DeepSeek · open weights

deepseek.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
MMLU60.5exact_matchN/AIndependentmediumarxiv.org
WinoGrande72.9accuracyN/AIndependentmediumarxiv.org

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K87.6exact_matchN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…