Le Chat: Custom MCP Connectors, Memories

I use Qwen Chat as my daily, it’s good and does the job very well. I have never thought about trying out Mistral, is their model good at anything? Any area it excels at? Or is it far behind all the other models?

Qwen is good for reasoning/feedback/creative work. I use it a lot when reviewing documentation, prose and some code, it's the one I like the most.

But when it comes to researching information is consistently among the worst performers in my comparisons.

Generally the order is Opus 4.1 > Perplexity > Gemini Pro >> GPT 5 >> Qwen.

By research you mean web search/deep research or only use knowledge embedded in llm? I use ChatGPT most of time, didn't find Claude work better for me, maybe I should switch if there is a big gap in performance.

Deep research, I don't trust LLMs with anything really.

I pay for Mistral pro and it is cheaper than other options ($15/mo) and you get some free metered API usage which works with a lot of different Ai coding products. They frequently add features with little fanfare (this time is a bit of an exception).

I find them to be a pretty good over-all model although not at the bleeding edge. Their responses are very fast. Qwen is better with code/log analysis in my experience but general coding questions hasn't presented any problems.

Mistral's agent framework is pretty good too. You can make agents very easily with the le chat side or if you want to have more deep control, you get le platforme access and agents you make there can be used in le chat without costing against API usage.

Of the AI products I've been working with, and I've been trying a lot of them, Mistral is one I plan on keeping when I reduce myself down to 2-3 I want to stick around.

I got Perplexity Pro one year for free, what makes Opus 4.1 search so good? Is it worth switching?

I don't know whether I can give you a conclusive answer, due to how query-dependent the results are and the lack of determinism.

I really like perplexity and if you get it free it's hard to justify spending 100$/month.

I understand, I thought maybe there was a couple of cases you stumbled upon that Opus 4.1 was better at, which made you rank it higher than Perplexity!

Yes this happened.

Few recent examples:

- find me public companies listed in Poland that have the best z-index of dividend yield, payout ratio and earnings growth

- list the most important psychological tendencies and biases that crew resource management tries to address