Model

DeepSeek-Coder-Instruct 33B

DeepSeek · open weights

deepseek.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
MMLU39.4exact_matchN/AIndependentmediumarxiv.org
WinoGrande62.0accuracyN/AIndependentmediumarxiv.org

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K35.4exact_matchN/AIndependentmediumarxiv.org

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
AlgoREval46.4accuracyN/AIndependentmediumarxiv.org
MBPP70.0accuracyN/AIndependentmediumarxiv.org
SAFIM69.0averageN/AIndependentmediumarxiv.org
SCCGBench2.9mockN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…