|
|
|
|
|
|
by girvo
27 days ago
|
|
|
Right and all of my own evals back this up for Gemma 4... ...except its notably worse at coding in an agent context even with a harness setup to do exactly what Google says it should do (wrt. to sending summarised thinking back and so on) So despite it being far better token efficiency wise, it's just worse for what I need to use it for compared to DSv4 Flash or Qwen 3.6 27B Such a shame, too. |
|
|