CodeChain + WizardCoder-15B

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Natural Language Processing4 results

Code GenerationonCodeContests
Test Set pass@1· 2023-10-13
2.35
best: 58.18 (EG-CFG (DeepSeek-V3-0324))
SOTA
CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules arXiv:2310.08992
Code GenerationonCodeContests
Test Set pass@5· 2023-10-13
3.29
best: 35.2 (MapCoder (GPT-4))
SOTA
CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules arXiv:2310.08992
Code GenerationonCodeContests
Val Set pass@1· 2023-10-13
2.48
best: 28.5 (MapCoder (GPT-4))
SOTA
CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules arXiv:2310.08992
Code GenerationonCodeContests
Val Set pass@5· 2023-10-13
3.3
SOTA
CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules arXiv:2310.08992