language benchmark
Multipl-E HumanEval
MultiPL-E is a scalable and extensible approach to benchmarking neural code generation that translates unit test-driven code generation benchmarks across multiple programming languages. It extends the HumanEval benchmark to 18 additional programming languages, enabling evaluation of code generation models across diverse programming paradigms and providing insights into how models generalize programming knowledge across language boundaries.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
Multipl-E HumanEval Ranking
Higher score ranks better on this benchmark.
| 01 | ME | 75.2% | 100.0% | 3 | C | |
| 02 | ME | 65.5% | 50.0% | 3 | C | |
| 03 | ME | 50.8% | 0.0% | 3 | C |
Multipl-E HumanEval Score Distribution
A closer view of the leading scores on this benchmark.
Multipl-E HumanEval Highlights
The leading models and scores on this benchmark.
What is Multipl-E HumanEval?
What Multipl-E HumanEval measures and how its scores work.
MultiPL-E is a scalable and extensible approach to benchmarking neural code generation that translates unit test-driven code generation benchmarks across multiple programming languages. It extends the HumanEval benchmark to 18 additional programming languages, enabling evaluation of code generation models across diverse programming paradigms and providing insights into how models generalize programming knowledge across language boundaries.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Multipl-E HumanEval
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- multipl-e-humaneval|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Multipl-E HumanEval.
Which model scores highest on Multipl-E HumanEval?
Llama 3.1 405B Instruct is currently ranked first with 75.2%.
What does Multipl-E HumanEval measure?
MultiPL-E is a scalable and extensible approach to benchmarking neural code generation that translates unit test-driven code generation benchmarks across multiple programming languages. It extends the HumanEval benchmark to 18 additional programming languages, enabling evaluation of code generation models across diverse programming paradigms and providing insights into how models generalize programming knowledge across language boundaries.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.