top | item 45693435

Experimental 3.5T K2 merge beats GPT-4.5 and Opus at writing

2 points| bo0tzz | 4 months ago |huggingface.co

1 comment

order

mynti|4 months ago

"beats at writing" is kind of far fetched since the page provides three generic pormpts with answers from Opus, GPT5 and K3. But a 3.5T model is crazy huge and the answers still feel more or less the same to the other models