DeepSeek-Coder-Base 6.7B (few-shot)

Reported on 1 benchmark across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing1 result

Code GenerationonMBPP
Accuracy· 2024-01-25
60.6
best: 96.6 (EG-CFG (DeepSeek-V3-0324))
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence arXiv:2401.14196