Metric: Test Set pass@1 (higher is better)
| # | Model↕ | Test Set pass@1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | EG-CFG (DeepSeek-V3-0324) | 58.18 | No | Execution Guided Line-by-Line Code Generation | 2025-06-12 | Code |
| 2 | LPW (GPT-4o) | 34.7 | No | Planning-Driven Programming: A Large Language Mo... | 2024-11-21 | Code |
| 3 | MapCoder (GPT-4) | 28.5 | No | MapCoder: Multi-Agent Code Generation for Compet... | 2024-05-18 | Code |
| 4 | CodeSim (GPT4) | 28.4 | No | CODESIM: Multi-Agent Code Generation and Problem... | 2025-02-08 | Code |
| 5 | MoTCoder-15B | 26.34 | No | MoTCoder: Elevating Large Language Models with M... | 2023-12-26 | Code |
| 6 | MoTCoder-7B-v1.5 | 20.77 | No | MoTCoder: Elevating Large Language Models with M... | 2023-12-26 | Code |
| 7 | CodeChain + WizardCoder-15B | 2.35 | No | CodeChain: Towards Modular Code Generation Throu... | 2023-10-13 | Code |
| 8 | WizardCoder-15B | 1.11 | No | WizardCoder: Empowering Code Large Language Mode... | 2023-06-14 | Code |