Who leads the MBPP benchmark?

Claude 3.5 Sonnet (Oct 2024) currently leads MBPP with a score of 91 on pass@1.

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

The state-of-the-art result on MBPP is 91 (pass@1), achieved by Claude 3.5 Sonnet (Oct 2024) as of 2026.

How many models are tracked on MBPP?

Codesota tracks 14 models on MBPP.

When was the MBPP leaderboard last updated?

The MBPP leaderboard on Codesota includes results through 2026.

Codesota · Benchmark · MBPPHome/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/

974 crowd-sourced Python programming problems suitable for beginners. Covers programming fundamentals and standard library.

Paper ↗Leaderboard ↓Lineage

§ 01 · Leaderboard

Results by metric.

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	Claude 3.5 Sonnet (Oct 2024) Fetched from CodeSOTA API on 2026-04-20	verified	91	2026	Source ↗	Looks wrong?
02	Qwen2.5-Coder-32B-Instruct Fetched from CodeSOTA API on 2026-04-20	verified	90.2	2026	Source ↗	Looks wrong?
03	DeepSeek-Coder-V2-Instruct Fetched from CodeSOTA API on 2026-04-20	verified	89.4	2026	Source ↗	Looks wrong?
04	claude-35-sonnet Fetched from CodeSOTA API on 2026-04-20	vendor	89.2	2026	Source ↗	Looks wrong?
05	gpt-4o Fetched from CodeSOTA API on 2026-04-20	vendor	87.8	2026	Source ↗	Looks wrong?
06	GPT-4o (Aug 2024) Fetched from CodeSOTA API on 2026-04-20	verified	86.8	2026	Source ↗	Looks wrong?
07	Qwen2.5-Coder-7B-Instruct Fetched from CodeSOTA API on 2026-04-20	verified	83.5	2026	Source ↗	Looks wrong?
08	Codestral 22B v0.1 Fetched from CodeSOTA API on 2026-04-20	verified	78.2	2026	Source ↗	Looks wrong?
09	Llama 4 Maverick (17B-128E) Fetched from CodeSOTA API on 2026-04-20	verified	77.6	2026	Source ↗	Looks wrong?
10	DeepSeek-V3 Fetched from CodeSOTA API on 2026-04-20	verified	75.4	2026	Source ↗	Looks wrong?
11	Gemma 3 27B IT Fetched from CodeSOTA API on 2026-04-20	verified	74.4	2026	Source ↗	Looks wrong?
12	Gemma 3 12B IT Fetched from CodeSOTA API on 2026-04-20	verified	73	2026	Source ↗	Looks wrong?
13	Llama 4 Scout (17B-16E) Fetched from CodeSOTA API on 2026-04-20	verified	67.8	2026	Source ↗	Looks wrong?
14	Gemma 3 4B IT Fetched from CodeSOTA API on 2026-04-20	verified	63.2	2026	Source ↗	Looks wrong?