MBPP

Dataset Card for Mostly Basic Python Problems (mbpp) Dataset Summary The benchmark consists of around 1,000 crowd-sourced Python programming problems, designed to be solvable by entry level programmers, covering programming fundamentals, standard library functionality, and so on. Each problem consists of a task descrip

Papers using MBPP (18)

Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains2026ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization2026Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference2026EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs2026Think Anywhere in Code Generation2026Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models2026Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval2026TGPR: Tree-Guided Policy Refinement for Robust Self-Debugging of LLMs2025From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs2025Efficient Code LLM Training via Distribution-Consistent and Diversity-Aware Data Selection2025Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search2025Learning to Insert [PAUSE] Tokens for Better Reasoning2025Learning to Generate Unit Tests for Automated Debugging2025CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models2025dParallel: Learnable Parallel Decoding for dLLMs2025Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks2025OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs2025