reasoning benchmark
MBPP ++ base version
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. This is an enhanced version with additional test cases.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
MBPP ++ base version leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ME | 86.0% | 100.0% | 1 | C |
MBPP ++ base version highlights
The top published results on this benchmark's own scale.
What is MBPP ++ base version?
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. Each problem consists of a task description, code solution, and 3 automated test cases covering programming fundamentals and standard library functionality. This is an enhanced version with additional test cases.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MBPP ++ base version
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mbpp-++-base-version|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MBPP ++ base version.
Which model scores highest on MBPP ++ base version?
Llama 3.1 70B Instruct is currently ranked first with 86.0%.
What does MBPP ++ base version measure?
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. This is an enhanced version with additional test cases.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 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.