> got a surprisingly good result
> the output wasn't even recognizably Danish
How would you know that it's good then?
I believe you misread. My reading is that Gemini 3 gave a good result on a certain input, so they gave the same input to this model and the result was poor.
Yes. I can also read maybe 60-80% of this document tolerably well myself, with effort.
You're correct.
I believe you misread. My reading is that Gemini 3 gave a good result on a certain input, so they gave the same input to this model and the result was poor.
Yes. I can also read maybe 60-80% of this document tolerably well myself, with effort.
You're correct.