From deb13c060c66519480ce0c7a989515a4de1beded Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Sun, 19 May 2024 15:14:22 -0700 Subject: [PATCH] copy --- docs/commands.md | 5 ++--- docs/leaderboards/index.md | 4 ++-- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/docs/commands.md b/docs/commands.md index 35cd9d7be..9f28d03c9 100644 --- a/docs/commands.md +++ b/docs/commands.md @@ -37,6 +37,5 @@ The interactive prompt is built with [prompt-toolkit](https://github.com/prompt- - `Ctrl-P` : Move up to the previous history entry. - `Ctrl-R` : Reverse search in command history. -Note: aider currently exits vi normal mode after a single command, (maybe something to do with the esc keybinding?). Feel free to investigate and make a PR if you would like to see it fully supported. - -Prompt toolkit also does not provide clear documentation on the bindings they support - maybe you can take aider and help them out with that and we can then link to the authoritative docs. +Note: aider currently exits vi normal mode after a single command, (maybe something to do with the esc keybinding?). +Feel free to investigate and make a PR if you would like to see it fully supported. diff --git a/docs/leaderboards/index.md b/docs/leaderboards/index.md index d33cc6a54..7fb8cf290 100644 --- a/docs/leaderboards/index.md +++ b/docs/leaderboards/index.md @@ -2,7 +2,7 @@ highlight_image: /assets/leaderboard.jpg --- -# GPT-4o takes #1 & #2 on the Aider LLM leaderboards +# Aider LLM Leaderboards Aider works best with LLMs which are good at *editing* code, not just good at writing code. @@ -14,7 +14,7 @@ The leaderboards below report the results from a number of popular LLMs. While [aider can connect to almost any LLM](/docs/llms.html), it works best with models that score well on the benchmarks. -## GPT-4o +## GPT-4o takes the #1 & #2 spots GPT-4o tops the aider LLM code editing leaderboard at 72.9%, versus 68.4% for Opus. GPT-4o takes second on aider's refactoring leaderboard with 62.9%, versus Opus at 72.3%.