From d0ebc7a810f2fbc82bc86f1fafbc90b6d0397b9b Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Thu, 25 Jul 2024 11:20:08 +0200 Subject: [PATCH] copy --- aider/website/_posts/2024-07-25-new-models.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/aider/website/_posts/2024-07-25-new-models.md b/aider/website/_posts/2024-07-25-new-models.md index b1d9d7bf2..5020d1d00 100644 --- a/aider/website/_posts/2024-07-25-new-models.md +++ b/aider/website/_posts/2024-07-25-new-models.md @@ -47,8 +47,8 @@ Llama 3.1 family of models, which have performed well on many evals. The flagship Llama 3.1 405B instruct only -secured #7 on aider's leaderboard. -This is well behind frontier models like +secured #7 on aider's leaderboard, +well behind frontier models like Claude 3.5 Sonnet & GPT-4o. The 405B model can use SEARCH/REPLACE to efficiently @@ -58,6 +58,9 @@ from 66% to 64%. The smaller 70B model was competitive with GPT-3.5, while the 8B model lags far behind. +Both seem unable to reliably use SEARCH/REPLACE to edit files. +This limits them to editing smaller files that can +fit into their output token limit. ## Mistral Large 2 (2407)