reasoning benchmark
Multipl-E MBPP
MultiPL-E extends the Mostly Basic Python Problems (MBPP) benchmark to 18+ programming languages for evaluating multilingual code generation capabilities. MBPP contains 974 crowd-sourced programming problems designed to be solvable by entry-level programmers, covering programming fundamentals and standard library functionality. Each problem includes a task description, code solution, and automated test cases.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
Multipl-E MBPP leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ME | 65.7% | 100.0% | 3 | C | |
| 2 | ME | 62.0% | 50.0% | 3 | C | |
| 3 | ME | 52.4% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
Multipl-E MBPP highlights
The top published results on this benchmark's own scale.
What is Multipl-E MBPP?
Definition and scoring fields from the benchmark registry.
MultiPL-E extends the Mostly Basic Python Problems (MBPP) benchmark to 18+ programming languages for evaluating multilingual code generation capabilities. MBPP contains 974 crowd-sourced programming problems designed to be solvable by entry-level programmers, covering programming fundamentals and standard library functionality. Each problem includes a task description, code solution, and automated test cases.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Multipl-E MBPP
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- multipl-e-mbpp|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Multipl-E MBPP.
Which model scores highest on Multipl-E MBPP?
Llama 3.1 405B Instruct is currently ranked first with 65.7%.
What does Multipl-E MBPP measure?
MultiPL-E extends the Mostly Basic Python Problems (MBPP) benchmark to 18+ programming languages for evaluating multilingual code generation capabilities. MBPP contains 974 crowd-sourced programming problems designed to be solvable by entry-level programmers, covering programming fundamentals and standard library functionality. Each problem includes a task description, code solution, and automated test cases.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.