APPS (Automated Programming Progress Standard)
by UC Berkeley · open-source · Last verified 2026-03-17
A benchmark of 10,000 programming problems at introductory, interview, and competitive programming difficulty levels, each with problem statements, test cases, and human-written solutions. APPS is the standard dataset for evaluating code generation models on realistic programming tasks ranging from simple loops to complex algorithmic challenges drawn from competitive programming platforms.
https://huggingface.co/datasets/codeparrot/apps ↗B+
B+—Good
Adoption: B+Quality: AFreshness: C+Citations: AEngagement: F
Specifications
- License
- MIT
- Pricing
- open-source
- Capabilities
- code-generation, evaluation, competitive-programming
- Integrations
- hugging-face
- Use Cases
- code-model-evaluation, competitive-programming-training, research
- API Available
- Yes
- Tags
- code, competitive-programming, evaluation, problem-solving, benchmark
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
70.3Adoption
77
Quality
89
Freshness
52
Citations
87
Engagement
0
Put AI to work for your business
Deploy this dataset alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.