Comment by ritzaco
11 hours ago
Any 'vibe check' on these; I don't have benchmarks but I tried out Le Chonk for general coding work that they claim it works really well at and I was very disappointed, it seemed to make all kinds of obvious errors of the kind that I haven't seen from opus, sol, deepseek flash etc in over a year
Just tested Mistral 4 too in Vibe and it's slow. It works well, but is way too slow. Switched back to Mistral's GLM5.3, which is awesome.
Edit : working with GLM5.3 now, it's also slow. Maybe Mistral's under heavy load.
Disclaimer : Not Cofounder of The Forecasting Company here
I've been using Mistral Large 4 and some of my other friends have as well.
Something is going on with the performance (as in speed of the service, not quality). Some days it's quite fast, some days it's so slow I interrupt it because I thought it was hanging.
I think they're shifting hosting capacity around, or otherwise messing with the model. Note that it's still a "preview" version, meaning they're still training it further for the final release and they are likely still figuring out the optimal hosting configuration as well.
It wouldn't surprise me to see further changes in both quality of the model and speed before the final release.
We are improving all layers of the stack (model, inference, harness) so do expect improvements in quality in perf over the following weeks.
<mistral vibe pm here>
How are you accessing Mistral 4 from Vibe? The only ones available on my end are Medium 3.5 and GLM-5.3 despite having a Pro subscription.
I updated my vibe config to point to Mistral 4 and it charges my subscription capacity, not my API allowance. So it is included in subscriptions, you just need to do a little bit of legwork.
We are rolling it out via A/B experiments and improving the experience as we roll-out. 100% of the users should see it in the following 7 days.
<mistral vibe pm here>
Location based maybe ? I'm in France.
6 replies →