← Code Generation

Papers with Code · CC BY-SA 4.0

APPS

아카이브 평가 18건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
LPW (GPT-4o)	Introductory Pass@1 87.2 Interview Pass@1 65.2 Competition Pass@1 34.8 Pass@1 62.6	Planning-Driven Programming: A Large Language Model Programming Workflow 2024-11-21	코드 1
MoTCoder-32B-V1.5	Introductory Pass@1 68.44 Interview Pass@1 44.49 Competition Pass@1 27.84	MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks 2023-12-26	코드 1
MoTCoder-7B-V1.5	Introductory Pass@1 54.26 Interview Pass@1 32.63 Competition Pass@1 21.18	MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks 2023-12-26	코드 1
code-davinci-002 175B (CodeT)	Introductory Pass@1 47.3% Interview Pass@1 14.3% Competition Pass@1 6.2%	CodeT: Code Generation with Generated Tests 2022-07-21	코드 1
deepseek-ai/deepseek-coder-6.7b-instruct	Introductory Pass@1 33.80 Interview Pass@1 19.70 Competition Pass@1 11.09	DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence 2024-01-25	코드 1
code-davinci-002 175B	Introductory Pass@1 31.92	CodeT: Code Generation with Generated Tests 2022-07-21	코드 1
CodeChain+WizardCoder-15b	Introductory Pass@1 29.3% Interview Pass@1 6.4% Competition Pass@1 2.5% Competition Pass@any 14.5% Interview Pass@any 25.4% Introductory Pass@any 60.9%	CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules 2023-10-13	코드 1
WizardCoder-15b	Introductory Pass@1 26.29 Interview Pass@1 7.49 Competition Pass@1 3.75	CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules 2023-10-13	코드 1
CodeSim (GPT4)	Introductory Pass@1 26.04 Interview Pass@1 4.21 Competition Pass@1 0.81	CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging 2025-02-08	코드 1
CodeRL+CodeT5	Introductory Pass@1 20 Interview Pass@1 13.5 Competition Pass@1 33.3	CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning 2022-07-05	코드 1 · 코드 2
GPT-J 6B (Finetuned)	Introductory Pass@1 6.77% Interview Pass@1 1.80% Competition Pass@1 0.69% Introductory Pass@1000 38.10% Interview Pass@1000 14.33% Competition Pass@1000 15.70% Competition Pass@5 2.36% Interview Pass@5 4.48% Introductory Pass@5 15.27% Competition Pass@any 15.70% Interview Pass@any 14.33% Introductory Pass@any 38.10%	CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning 2022-07-05	코드 1 · 코드 2
Codex 12B (Raw)	Introductory Pass@1 5.60% Interview Pass@1 1.00% Competition Pass@1 0.50% Introductory Pass@1000 35.20% Interview Pass@1000 13.15% Competition Pass@1000 13.51% Competition Pass@5 1.00% Interview Pass@5 1.73% Introductory Pass@5 9.20% Competition Pass@any 13.51% Interview Pass@any 13.15% Introductory Pass@any 35.20%	Evaluating Large Language Models Trained on Code 2021-07-07	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13
GPT-Neo 2.7B (Finetuned)	Introductory Pass@1 4.14% Interview Pass@1 0.14% Competition Pass@1 0.02% Introductory Pass@1000 25.02% Interview Pass@1000 3.70% Competition Pass@1000 3.23% Competition Pass@5 0.09% Interview Pass@5 0.51% Introductory Pass@5 9.65% Competition Pass@any 3.32% Interview Pass@any 3.70% Introductory Pass@any 25.02%	CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning 2022-07-05	코드 1 · 코드 2
GPT-Neo 2.7B	Introductory Pass@1 3.90% Interview Pass@1 0.57% Competition Pass@1 0.00% Introductory Pass@1000 27.90% Interview Pass@1000 9.83% Competition Pass@1000 11.40% Competition Pass@5 0.00% Interview Pass@5 0.80% Introductory Pass@5 5.50% Competition Pass@any 11.40% Interview Pass@any 9.83% Introductory Pass@any 27.90%	Measuring Coding Challenge Competence With APPS 2021-05-20	코드 1 · 코드 2 · 코드 3
GPT2 1.5B (Finetuned)	Introductory Pass@1 3.90% Interview Pass@1 0.57% Competition Pass@1 0.00% Competition Pass@5 0.00% Interview Pass@5 0.80% Introductory Pass@5 5.50% Competition Pass@any 0.0% Interview Pass@any 0.80% Introductory Pass@any 5.50%	CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning 2022-07-05	코드 1 · 코드 2
MapCoder APPS-150-cherrypicked (GPT-4)	Introductory Pass@1 1.30% Interview Pass@1 0.70% Competition Pass@1 0.00% Introductory Pass@1000 25.00% Interview Pass@1000 9.27% Competition Pass@1000 8.80% Competition Pass@5 0.00% Interview Pass@5 1.03% Introductory Pass@5 3.60% Competition Pass@any 8.80% Interview Pass@any 9.27% Introductory Pass@any 25.00%	MapCoder: Multi-Agent Code Generation for Competitive Problem Solving 2024-05-18	코드 1 · 코드 2
AlphaCode 1B Filtered from 50000	Competition Pass@any 22.0	Competition-Level Code Generation with AlphaCode 2022-02-08	코드 1 · 코드 2
AlphaCode 1B	Competition Pass@5 7.75% Interview Pass@5 9.66% Introductory Pass@5 20.36% Competition Pass@any 7.75% Interview Pass@any 9.66% Introductory Pass@any 20.36%	Competition-Level Code Generation with AlphaCode 2022-02-08	코드 1 · 코드 2