I guess even if you win 0.1 cents/day with a bot, it's just scalling afterward

Are there any benchmarks that exist for those 24 languages?

The detailed results are in appendix to the paper: https://arxiv.org/abs/2506.04079

It's on the huggingface readme

https://huggingface.co/utter-project/EuroLLM-9B#results

https://huggingface.co/utter-project/EuroLLM-9B#english

It's more like the default is to be ranked near the bottom unless your comment gets traction during the brief window of time it is ranked first for being new. Seeing your comments go splat after that window expires is not some nefarious conspiracy..

Oh, you'd be surprised to know what's behind many of those "conspiracies"!

Does someone have the benchmarks compared to other models?

claude 3.7 no thinking (diff) - 60.4%

claude 3.7 32k thinking tokens (diff) - 64.9%

GPT-4.1 (diff) - 52.9% (stat is from the blog post)

https://aider.chat/docs/leaderboards/

Location: Europe (Turin, Italy) Remote: Worldwide can adapt to timezone, can also travel if needed ofr hybrid. Willing to relocate: Yes but in a July 2026! Technologies: Python, Kubernetes, Asp.Net, React, ELK and many more Résumé/CV: https://drive.google.com/file/d/1RlscJr5Lv9oooa0hW14Xz_zoAQP... Email: elias.thouant <at> gmail.com