reasoning benchmark
MBPP EvalPlus
MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. EvalPlus extends MBPP with significantly more test cases (35x) for more rigorous evaluation of LLM-synthesized code, providing high-quality and precise evaluation.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
MBPP EvalPlus leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ME | 88.6% | 100.0% | 2 | C | |
| 2 | ME | 87.6% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
MBPP EvalPlus highlights
The top published results on this benchmark's own scale.
What is MBPP EvalPlus?
Definition and scoring fields from the benchmark registry.
MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. EvalPlus extends MBPP with significantly more test cases (35x) for more rigorous evaluation of LLM-synthesized code, providing high-quality and precise evaluation.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MBPP EvalPlus
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mbpp-evalplus|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MBPP EvalPlus.
Which model scores highest on MBPP EvalPlus?
Llama 3.1 405B Instruct is currently ranked first with 88.6%.
What does MBPP EvalPlus measure?
MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. EvalPlus extends MBPP with significantly more test cases (35x) for more rigorous evaluation of LLM-synthesized code, providing high-quality and precise evaluation.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.