reasoning benchmark
MBPP+
MBPP+ is an enhanced version of MBPP (Mostly Basic Python Problems) with significantly more test cases (35x) for more rigorous evaluation. MBPP is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers, covering programming fundamentals and standard library functionality.
Updated Aug 7, 2026
Published models4
Registry coverage4
MetricScore
EvidenceB
MBPP+ leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 20 | XI | 74.1% | 47.2% | 37 | C | |
| 26 | AC | 67.2% | 30.6% | 37 | C | |
| 31 | AC | 63.2% | 16.7% | 37 | C | |
| 36 | BA | 40.2% | 2.8% | 37 | C |
Score distribution
Top published rows on the benchmark's original scale.
MBPP+ highlights
The top published results on this benchmark's own scale.
What is MBPP+?
Definition and scoring fields from the benchmark registry.
MBPP+ is an enhanced version of MBPP (Mostly Basic Python Problems) with significantly more test cases (35x) for more rigorous evaluation. MBPP is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers, covering programming fundamentals and standard library functionality.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MBPP+
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mbpp+|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MBPP+.
Which model scores highest on MBPP+?
MiMo-V2.5-Pro is currently ranked first with 74.1%.
What does MBPP+ measure?
MBPP+ is an enhanced version of MBPP (Mostly Basic Python Problems) with significantly more test cases (35x) for more rigorous evaluation. MBPP is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers, covering programming fundamentals and standard library functionality.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 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.