Code Generation
Code Generation is an important field to predict explicit code or program structure from multimodal data sources such as incomplete code, programs in another programming language, natural language descriptions or execution examples. Code Generation tools can assist the development of automatic programming tools to improve programming productivity.
Source: Deep Learning for Source Code Modeling and Generation
Image source: Measuring Coding Challenge Competence With APPS
Papers
Showing 1–10 of 1697 papers
All datasetsMBPPAPPSCoNaLaDjangoWikiSQLRES-QCodeContestsHumanEvalPECCWebApp1K-ReactCoNaLa-ExtWebApp1k-Duo-React
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | EG-CFG (DeepSeek-V3-0324) | Accuracy | 96.6 | — | Unverified |
| 2 | QualityFlow (Sonnet-3.5) | Accuracy | 94.2 | — | Unverified |
| 3 | o1-mini + MapCoder (Hamming.ai) | Accuracy | 93.2 | — | Unverified |
| 4 | MGDebugger (DeepSeek-V3-0324) | Accuracy | 92.4 | — | Unverified |
| 5 | GPT-4 + AgentCoder | Accuracy | 91.8 | — | Unverified |
| 6 | CodeSim (GPT4o) | Accuracy | 90.7 | — | Unverified |
| 7 | Jiutian-大模型 | Accuracy | 90 | — | Unverified |
| 8 | GPT-3.5 Turbo (ChatGPT) + AgentCoder | Accuracy | 89.9 | — | Unverified |
| 9 | MapCoder (GPT-4o) | Accuracy | 89.7 | — | Unverified |
| 10 | GPT-4 (ChatGPT Plus) | Accuracy | 87.5 | — | Unverified |