Who leads the MBPP+ benchmark?

Qwen2.5-Coder-32B currently leads MBPP+ with a score of 76.4 on pass@1.

What is the state-of-the-art score on MBPP+?

The state-of-the-art result on MBPP+ is 76.4 (pass@1), achieved by Qwen2.5-Coder-32B as of 2026.

How many models are tracked on MBPP+?

Codesota tracks 4 models on MBPP+.

When was the MBPP+ leaderboard last updated?

The MBPP+ leaderboard on Codesota includes results through 2026.

Codesota · Benchmark · MBPP+Home/Leaderboards/Code & Software Engineering/Code Generation/MBPP+

Unknown

MBPP+.

Name: MBPP+ Benchmark Results
Creator: Unknown
Published: 2026-01-01
License: https://creativecommons.org/licenses/by/4.0/

Extended MBPP with additional test cases. Uses 399 hand-verified problems from MBPP-sanitized.

Paper ↗Leaderboard ↓Lineage

§ 01 · Leaderboard

Results by metric.

Only 4 models on this benchmark

Help build the community leaderboard — submit your model results.

Found a wrong score or missing run?

Use row edits to send a sourced correction into moderation.

Add / edit result ↗Report issue ↗

pass@1

Pass@1 is the reported evaluation metric for MBPP+. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for pass@1verifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

Rank	Model	Trust	Score	Year	Links	Fix
01	Qwen2.5-Coder-32B Fetched from CodeSOTA API on 2026-04-20	verified	76.4	2026	Source ↗	Looks wrong?
02	DeepSeek-V3 Fetched from CodeSOTA API on 2026-04-20	verified	73	2026	Source ↗	Looks wrong?
03	GPT-4o Fetched from CodeSOTA API on 2026-04-20	verified	71.2	2026	Source ↗	Looks wrong?
04	DeepSeek-Coder-33B Fetched from CodeSOTA API on 2026-04-20	verified	66	2026	Source ↗	Looks wrong?