Model

DeepSeek-R1-Distill-Qwen-14B

DeepSeek · open weights

deepseek.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
GPQA Diamond44.7accuracyN/AIndependenthighepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
AlgoREval39.6accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…