Model

DeepSeek-V3.1-Terminus

DeepSeek · open weights

deepseek.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CritPt1.7accuracyN/AIndependentlowepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
SciCode40.6scoreN/AIndependentmediumartificialanalysis.ai

Reproduced by the community

Loading community runs…