Code Models · 2022
AlphaCode (Competition-Level Code Generation)
AlphaCode showed that a transformer trained on public code plus massive sampling and test-based filtering could solve competitive programming problems at roughly median-human level, turning code generation from single-shot guessing into a search-and-filter pipeline.
Editorial record
Plain-language summary
AlphaCode generates a very large pool of candidate programs per problem (up to millions), then filters them by running the provided example tests and clusters the survivors by their behavior on generated inputs to pick a small number to submit. This sample-filter-cluster loop, rather than a single accurate decode, is what let it reach an average ranking around the top 54% of participants on Codeforces contests. It demonstrated that hard, multi-step reasoning problems could be approached by trading inference-time compute for correctness when an execution oracle is available.
Knowledge graph
Relationships
Descendants
ExtendsEvidence: Strongly supported
Codex: Evaluating LLMs Trained on Code (HumanEval)
AlphaCode extends code gen with search
P-341
Source record
Provenance
- Record ID
- P-341
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2203.07814
- arXiv:2203.07814
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.