This commit is contained in:
Paul Gauthier 2025-01-24 09:05:53 -08:00
parent ee5d72301a
commit 2d424e078e

View file

@ -23,8 +23,8 @@ Aider supports using a pair of models for coding:
[aider polyglot benchmark](/2024/12/21/polyglot.html).
They achieve this at **14X less cost** compared to the previous o1 SOTA result.
Using o1 or R1 as architect with various other editor models didn't produce significantly
better results than using them alone.
o1 paired with Sonnet didn't produce better results than just using o1 alone.
No other editor models tried improved o1 or R1 compared to their solo results.
This is in contrast to the first wave of thinking models like o1-preview and o1-mini,
which improved when paired with many different editor models.