Who leads the APPS benchmark?

CodeLlama-34B currently leads APPS with a score of 32.81 on pass@5.

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

The state-of-the-art result on APPS is 32.81 (pass@5), achieved by CodeLlama-34B as of 2026.

How many models are tracked on APPS?

Codesota tracks 3 models on APPS.

When was the APPS leaderboard last updated?

The APPS leaderboard on Codesota includes results through 2026.

Codesota · Benchmark · APPSHome/Leaderboards/Code & Software Engineering/Code Generation/APPS

Unknown

APPS.

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

10,000 coding problems from Codewars, AtCoder, Kattis, and CodeForces. Ranges from introductory to competition level.

Paper ↗Leaderboard ↓

§ 01 · Leaderboard

Results by metric.

Only 3 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@5

Pass@5 is the reported evaluation metric for APPS. 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@5verifiedpapervendorcommunityunverified

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	CodeLlama-34B Fetched from CodeSOTA API on 2026-04-20	verified	32.81	2026	Source ↗	Looks wrong?
02	CodeLlama-13B Fetched from CodeSOTA API on 2026-04-20	verified	23.74	2026	Source ↗	Looks wrong?
03	CodeLlama-7B Fetched from CodeSOTA API on 2026-04-20	verified	10.76	2026	Source ↗	Looks wrong?

§ 04 · Submit a result

Add to the leaderboard.

Submit a Result

← Back to Code Generation