reasoning benchmark
MBPP pass@1
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. This variant uses pass@1 evaluation metric measuring the percentage of problems solved correctly on the first attempt.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
MBPP pass@1 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MA | 70.0% | 100.0% | 1 | C |
MBPP pass@1 highlights
The top published results on this benchmark's own scale.
What is MBPP pass@1?
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. This variant uses pass@1 evaluation metric measuring the percentage of problems solved correctly on the first attempt.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MBPP pass@1
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mbpp-pass@1|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MBPP pass@1.
Which model scores highest on MBPP pass@1?
Ministral 8B Instruct is currently ranked first with 70.0%.
What does MBPP pass@1 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. This variant uses pass@1 evaluation metric measuring the percentage of problems solved correctly on the first attempt.
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.