Aider-Edit

DeepSeek-V3 79.7% leads since Dec 2024 Dropped

Models edit Python source files to complete 133 Exercism exercises through Aider. Scored by the share of exercises whose unit tests all pass.

Aider replaced it with the polyglot benchmark in December 2024 because top scores passed 80% on its 133 Python exercises.

Made by Aider Released Jul 2023 Function-level problems All tasks public Last in a launch post Jul 2025 , dropped for a newer version Last model added Oct 2025 Scores refreshed 2 Nov 2026

Level: School Students, from grade school to high school
Scored: Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers: Code A program or patch run against tests.

Aider-AI/aider 49,868 stars Leaderboard aider.chat

Models scored in lab cards

Launch posts list it, from 2 labs

System cards report it, from 3 labs

DeepSeek-V3 leads with 79.7% among models released by Oct 2025

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Bars Table

The newest model with a score here came out in Oct 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

#	Model	Score	Date	Source
1	DeepSeek-V3	79.7%	Dec 2024	Model card
2	Ring-1T	78.6%	Oct 2025	Model card
3	DeepSeek-V2.5 Sep 2024	72.2%	Sep 2024	Model card
4	Seed-Coder-8B-Instruct	57.1%	Jun 2025	Model card
5	Seed Diffusion Preview	44.4%	Jul 2025	Model card

The benchmark's own leaderboard has 92 entries, 37 of them models we track. We plot every source in the charts below.

4 models have held number one since its release in Jul 2023

Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.

OpenAI Anthropic DeepSeek

Own leaderboard Replaced by Aider Polyglot, Dec 2024

Claude 3.5 Sonnet 84.2%

Lab claims Not tested since Oct 2025

DeepSeek-V3 79.7%

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far

Labs moved on to Aider Polyglot

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

DeepSeek

ByteDance Seed

Date	Launch post	Score	As the post writes it
31 Jul 2025	Seed Diffusion Preview	44.4	Aider (whole format, tries=2)
26 Dec 2024	DeepSeek-V3	79.7	Aider-Edit (Acc.)
5 Sep 2024	DeepSeek-V2.5	72.2	Aider

4 system cards report it, from 3 labs

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
21 Oct 2025	Ring-1T technical report	78.6	Aider, cited as aider.chat/docs/benchmarks.html#the-benchmark (Table 1)	Capabilities
4 Aug 2025	Seed Diffusion Preview technical report	44.4	Aider, whole format, tries=2 (Table 1)	Capabilities
4 Jun 2025	Seed-Coder-8B-Instruct technical report	57.1	Aider ("whole" format) tries=2 (Table 13)	Capabilities
26 Dec 2024	DeepSeek-V3 technical report	79.7	Aider-Edit (Acc.), DeepSeek-V3 (Table 6)	Capabilities

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

OpenAI Anthropic Google DeepMind

Aider Polyglot Passed 85% in Aug 2025, by GPT-5

GPT-5 88%

Aider-Edit Not tested since Oct 2025