MBPP Plus

MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. Each problem consists of a task description, code solution, and 3 automated test cases covering programming fundamentals and standard library functionality. This is an enhanced version with additional test cases for more rigorous evaluation.

Mistral Small 3.2 24B Instruct from Mistral AI currently leads the MBPP Plus leaderboard with a score of 0.783 across 1 evaluated AI models.

Paper

Progress Over Time

Interactive timeline showing model performance evolution on MBPP Plus

State-of-the-art frontier
Open
Proprietary

MBPP Plus Leaderboard

1 models
ContextCostLicense
124B
Notice missing or incorrect data?

FAQ

Common questions about MBPP Plus.

What is the MBPP Plus benchmark?

MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. Each problem consists of a task description, code solution, and 3 automated test cases covering programming fundamentals and standard library functionality. This is an enhanced version with additional test cases for more rigorous evaluation.

What is the MBPP Plus leaderboard?

The MBPP Plus leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Mistral Small 3.2 24B Instruct by Mistral AI leads with a score of 0.783. The average score across all models is 0.783.

What is the highest MBPP Plus score?

The highest MBPP Plus score is 0.783, achieved by Mistral Small 3.2 24B Instruct from Mistral AI.

How many models are evaluated on MBPP Plus?

1 models have been evaluated on the MBPP Plus benchmark, with 0 verified results and 1 self-reported results.

Where can I find the MBPP Plus paper?

The MBPP Plus paper is available at https://arxiv.org/abs/2108.07732. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does MBPP Plus cover?

MBPP Plus is categorized under code and reasoning. The benchmark evaluates text models.

More evaluations to explore

Related benchmarks in the same category

View all code
GPQA

A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.

reasoning
213 models
MMLU-Pro

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.

reasoning
119 models
AIME 2025

All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.

reasoning
107 models
MMLU

Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains

reasoning
99 models
SWE-Bench Verified

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

code
89 models
Humanity's Last Exam

Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

reasoningmultimodal
74 models