aider + gemini is unbelievably good in established Effect | TypeScript at Scale codebases. forget Effect being good guide rails for developers (it still is), it’s an even better guide rails for AI. actually kind of shocked atm

Llama 4 Maverick scored 16% on the aider polyglot coding benchmark. aider.chat/docs/leaderboa…

OpenRouter's latest mystery model Optimus Alpha scored 53% on the aider polyglot leaderboard. This places it in the middle of the pack with Quasar, o3-mini-medium, Grok 3, etc. Available in aider v0.81.2: aider --model optimus aider.chat/docs/leaderboa…

My life has changed this week. There's finally an AI coding tool that's good enough to keep up with me. It's called "Aider". It's a front end that knows how to talk to any model that speaks the standard JSON API, and knows how to work git, and has been cleverly and effectively

Awesome seeing the Aider polygot benchmark by Paul Gauthier become a Tier 1 / go to benchmark by top labs

OpenAI's new GPT 4.1 scored 52% on the aider polyglot coding benchmark, in the middle of the pack near Grok 3 and DeepSeek V3. aider.chat/docs/leaderboa… Aider v0.82 is out w/support for GPT 4.1, mini & nano. Aider wrote 92% of the code in this release. aider.chat/HISTORY.html

Using o3-high as architect and gpt-4.1 as editor produced a new SOTA of 83% on the aider polyglot coding benchmark. It also substantially reduced costs, compared to o3-high alone. Use this powerful model combo like this: aider --model o3 --architect aider.chat/docs/leaderboa…

OpenHands LM 32B v0.1 scored 10% on the aider polyglot coding benchmark. Accessed via OpenRouter. aider.chat/docs/leaderboa…

Gemini 2.5 Flash scored 47% on the aider polyglot coding benchmark. See the attached graph where it is shown with other models for comparison/scale. aider.chat/docs/leaderboa…