Aider blog | xifan.uno

Reliably packaging & distributing python CLI tools is hard. Aider uses uv in novel ways to make it easy to install the aider CLI, its dependencies and python 3.12. All in an isolated env.

JAN 15, 2025

o1 tops aider's new polyglot leaderboard

o1 scores the top result on aider's new multi-language, more challenging coding benchmark.

[

Highlight Image

](https://aider.chat/2024/12/21/polyglot.html)

DEC 21, 2024

QwQ is a code architect, not an editor

QwQ is reasoning model like o1, and needs to be used as an architect with another model as editor.

[

Highlight Image

](https://aider.chat/2024/12/03/qwq.html)

DEC 3, 2024

Details matter with open source models

Open source LLMs are becoming very powerful, but pay attention to how you (or your provider) are serving the model. It can affect code editing skill.

[

Highlight Image

](https://aider.chat/2024/11/21/quantization.html)

NOV 21, 2024

Separating code reasoning and editing

An Architect model describes how to solve the coding problem, and an Editor model translates that into file edits. This Architect/Editor approach produces SOTA benchmark results.

[

Highlight Image

](https://aider.chat/2024/09/26/architect.html)

SEP 26, 2024

o1-preview is SOTA on the aider leaderboard

Preliminary benchmark results for the new OpenAI o1 models.

SEP 12, 2024

Sonnet seems as good as ever

Sonnet's score on the aider code editing benchmark has been stable since it launched.

[

Highlight Image

](https://aider.chat/2024/08/26/sonnet-seems-fine.html)

AUG 26, 2024

LLMs are bad at returning code in JSON

LLMs write worse code if you ask them to return the code wrapped in JSON via a tool function call.

[

Highlight Image

](https://aider.chat/2024/08/14/code-in-json.html)

AUG 14, 2024

Coding with Llama 3.1, new DeepSeek Coder & Mistral Large

Summary of code editing skill for the new models, with Sonnet and GPT-3.5 for scale.

[

Highlight Image

](https://aider.chat/2024/07/25/new-models.html)

JUL 25, 2024

Sonnet is the opposite of lazy

Claude 3.5 Sonnet can easily write more good code than fits in one 4k token API response.

[

Highlight Image

](https://aider.chat/2024/07/01/sonnet-not-lazy.html)

JUL 1, 2024

Aider is SOTA for both SWE Bench and SWE Bench Lite

Aider sets SOTA for the main SWE Bench, after recently setting SOTA for the Lite version.

[

Highlight Image

](https://aider.chat/2024/06/02/main-swe-bench.html)

JUN 2, 2024

Aider has written 7% of its own code (outdated, now 70%)

This article is quite out dated. Aider is currently writing about 70% of the new code in each release.

[

Highlight Image

](https://aider.chat/2024/05/24/self-assembly.html)

MAY 24, 2024

How aider scored SOTA 26.3% on SWE Bench Lite

Aider achieved this result mainly through its existing features that focus on static code analysis, reliable LLM code editing, and pragmatic UX for AI pair programming.

[

Highlight Image

](https://aider.chat/2024/05/22/swe-bench-lite.html)

MAY 22, 2024

Linting code for LLMs with tree-sitter

Aider now lints code after every LLM edit and automatically fixes errors, using tree-sitter and AST-aware code context.

[

Highlight Image

](https://aider.chat/2024/05/22/linting.html)

MAY 22, 2024

Drawing graphs with aider, GPT-4o and matplotlib

Use GPT-4o to draw graphs with matplotlib, including adjusting styles and making visual changes. You get the graph, but you also get the code in your repo.

[

Highlight Image

](https://aider.chat/2024/05/13/models-over-time.html)

MAY 13, 2024

Aider in your browser

Aider has an experimental browser UI, allowing you to collaborate with LLMs on code in your local git repo.

[

Highlight Image

](https://aider.chat/2024/05/02/browser.html)

MAY 2, 2024

GPT-4 Turbo with Vision is a step backwards for coding

OpenAI's GPT-4 Turbo with Vision model scores worse on aider's code editing benchmarks than all the previous GPT-4 models. In particular, it seems much more prone to "lazy coding" than the existing GPT-4 Turbo "preview" models.

[

Highlight Image