|
|
|
Opus 4.7 vs. Sonnet 4.6
|
|
3 points
by vdelpuerto
32 days ago
|
|
By standard I use Opus 4.7 for every task no matter what it is
with Claude. But, because I was reaching almost 90% of the model
use and with two days left before refresh I set Sonnet 4.6 for a
simple task with my Price analyst agent. And it was kind of painful.
It just had to look at an email from a client requesting a quotation,
look for the database of our usual values, scope analysis according
to the request and it was not the same as with Opus. So, bottom
line: not very sure if I can trust lower models with daily tasks
where you need to delegate and stay confident it won't require too
much iteration on those kinds of requests. |
|
One strategy I never had luck with was to have the smart model do an eval loop where it instructs the smaller model until it does the task. The problem is that the large model is way to prescriptive. This will improve in the near future because model labs are very focused on subagents