MBPP
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.
Sarvam-30B from Sarvam AI currently leads the MBPP leaderboard with a score of 0.927 across 33 evaluated AI models.
Sarvam-30B leads with 0.9%, followed by 
Llama-3.3 Nemotron Super 49B v1 at 0.9% and 
Qwen2.5-Coder 32B Instruct at 0.9%.
Progress Over Time
Interactive timeline showing model performance evolution on MBPP
MBPP Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Sarvam AI | 30B | — | — | ||
| 2 | 50B | — | — | |||
| 3 |  Alibaba Cloud / Qwen Team | 32B | — | — | ||
| 4 |  OpenBMB | 9B | — | — | ||
| 5 | Alibaba Cloud / Qwen Team | 73B | — | — | ||
| 6 | 8B | — | — | |||
| 7 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 7 | Alibaba Cloud / Qwen Team | 34B | — | — | ||
| 9 | Alibaba Cloud / Qwen Team | 7B | — | — | ||
| 10 | Alibaba Cloud / Qwen Team | 15B | — | — | ||
| 11 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 12 |  Microsoft | 60B | — | — | ||
| 13 | Alibaba Cloud / Qwen Team | 72B | — | — | ||
| 14 | Alibaba Cloud / Qwen Team | 8B | — | — | ||
| 15 |  Mistral AI | 22B | — | — | ||
| 16 |  Meta | 400B | — | — | ||
| 17 |  Google | — | — | — | ||
| 18 | Mistral AI | 24B | — | — | ||
| 19 | Google | 27B | — | — | ||
| 20 | Alibaba Cloud / Qwen Team | 7B | — | — | ||
| 21 | Google | 12B | — | — | ||
| 22 | Mistral AI | 24B | — | — | ||
| 23 | Microsoft | 4B | — | — | ||
| 24 | Meta | 109B | — | — | ||
| 25 | Alibaba Cloud / Qwen Team | 8B | — | — | ||
| 26 | Google | 8B | — | — | ||
| 26 | 2B | — | — | |||
| 28 | Google | 4B | — | — | ||
| 29 | Google | 27B | — | — | ||
| 30 | Google | 8B | — | — | ||
| 30 | 2B | — | — | |||
| 32 | Google | 9B | — | — | ||
| 33 | Google | 1B | — | — |
FAQ
Common questions about MBPP.
More evaluations to explore
Related benchmarks in the same category
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.
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.
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.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
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.
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