language benchmark
MultiPL-E Leaderboard
MultiPL-E is a scalable and extensible system for translating unit test-driven code generation benchmarks to multiple programming languages. It extends HumanEval and MBPP Python benchmarks to 18 additional programming languages, enabling evaluation of neural code generation models across diverse programming paradigms and language features.
Updated Aug 17, 2026
Models13
Model coverage13
MetricScore
EvidenceB
MultiPL-E Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score87.9% | Percentile100.0% | Participants13 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score87.8% | Percentile91.7% | Participants13 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score86.1% | Percentile83.3% | Participants13 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score85.7% | Percentile75.0% | Participants13 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score85.7% | Percentile66.7% | Participants13 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score75.4% | Percentile58.3% | Participants13 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score75.1% | Percentile50.0% | Participants13 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score72.8% | Percentile41.7% | Participants13 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score70.4% | Percentile33.3% | Participants13 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score69.2% | Percentile25.0% | Participants13 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score65.9% | Percentile16.7% | Participants13 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score65.8% | Percentile8.3% | Participants13 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score59.1% | Percentile0.0% | Participants13 | EvidenceC | Evaluated |
MultiPL-E Highlights
The leading models and scores on this benchmark.
MultiPL-E Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MultiPL-E
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis multipl-e AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACQwen3-235B-A22B-Instruct-2507Alibaba Cloud / Qwen Team
- Score
- 87.9%
- Price
- $0.70 input / $2.8 output per 1M tokens
- Speed
- Up to 68 tok/s via Fireworks
Strengths
- Ranks #1 of 13 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures MultiPL-E, not total model capability
- 02ACQwen3-Next-80B-A3B-InstructAlibaba Cloud / Qwen Team
- Score
- 87.8%
- Price
- $0.50 input / $2.0 output per 1M tokens
Strengths
- Ranks #2 of 13 compared models
- 92th percentile on this benchmark
- C evidence result
Considerations
- This result measures MultiPL-E, not total model capability
- 03ACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen Team
- Score
- 86.1%
Strengths
- Ranks #3 of 13 compared models
- 83th percentile on this benchmark
- C evidence result
Considerations
- This result measures MultiPL-E, not total model capability
- 04MAKimi K2 InstructMoonshot AI
- Score
- 85.7%
- Price
- $0.60 input / $2.5 output per 1M tokens
- Speed
- Up to 45 tok/s via Novita
Strengths
- Ranks #4 of 13 compared models
- 75th percentile on this benchmark
- C evidence result
Considerations
- This result measures MultiPL-E, not total model capability
- 05MAKimi K2-Instruct-0905Moonshot AI
- Score
- 85.7%
- Price
- $0.60 input / $2.5 output per 1M tokens
- Speed
- Up to 45 tok/s via Novita
Strengths
- Ranks #5 of 13 compared models
- 67th percentile on this benchmark
- C evidence result
Considerations
- This result measures MultiPL-E, not total model capability
Selection summary
Best AI Models for MultiPL-E
Qwen3-235B-A22B-Instruct-2507 currently leads MultiPL-E with 87.9%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is MultiPL-E?
What MultiPL-E measures and how its scores work.
MultiPL-E is a scalable and extensible system for translating unit test-driven code generation benchmarks to multiple programming languages. It extends HumanEval and MBPP Python benchmarks to 18 additional programming languages, enabling evaluation of neural code generation models across diverse programming paradigms and language features.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MultiPL-E
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- multipl-e|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MultiPL-E.
Which model scores highest on MultiPL-E?
Qwen3-235B-A22B-Instruct-2507 is currently ranked first with 87.9%.
What does MultiPL-E measure?
MultiPL-E is a scalable and extensible system for translating unit test-driven code generation benchmarks to multiple programming languages. It extends HumanEval and MBPP Python benchmarks to 18 additional programming languages, enabling evaluation of neural code generation models across diverse programming paradigms and language features.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
13 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.