Comment by pseudony
22 days ago
Made a Ask HN, but screwed it up by editing the text.
Anyway, good ideas/tools for evaluating LLMs ? Naturally, as a Dane, I am moving away from Claude, but I’d like more than a gut feel about how much I may have given up to do so.
You might benefit from LMArena's Leaderboard. It does not have Danish (yet), but German and English evaluation might help: https://lmarena.ai/de/leaderboard/text/german
Openrouter.ai shows the location of providers, you can find just a few European services, but also Singaporean and Canadian. Unfortunately, I could not find a way to filter easily.
Just go for Qwen or Deepseek. They are both very good.
Or Mistral, it is French and has been great for my day to day queries (haven't tried for programming yet).
Mistral has made a pivot from small model focus to large model focus by getting into bed with Microsoft. I don't know how sticky their deals are but, taking a quick look at recent Microsoft press releases, Mistral still seems to be prioritizing releases on Azure.
1 reply →