deepseek-ai/deepseek-coder-6.7b-instruct

Reported on 3 benchmarks 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 Processing3 results

Code GenerationonAPPS
Competition Pass@1· 2024-01-25
11.09
best: 34.8 (LPW (GPT-4o))
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence arXiv:2401.14196
Code GenerationonAPPS
Interview Pass@1· 2024-01-25
19.7
best: 65.2 (LPW (GPT-4o))
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence arXiv:2401.14196
Code GenerationonAPPS
Introductory Pass@1· 2024-01-25
33.8
best: 87.2 (LPW (GPT-4o))
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence arXiv:2401.14196