One thing about Anthropic/OpenAI models is they go off the rails with lots of conversation turns or long contexts. Like when they need to remember a lot of vending machine conversation I guess.
Gemini is much better. TBH the only models I’ve seen that are half decent at this are:
“Alternate attention” models like Gemini, Jamba Large or Falcon H1, depending on the iteration. Some recent versions of Gemini kinda lose this, then get it back.
Models finetuned specifically for this, like roleplay models or the Samantha model trained on therapy-style chat.
But most models are overtuned for oneshots like fix this table or write me a function, and don’t invest much in long context performance because it’s not very flashy.
One thing about Anthropic/OpenAI models is they go off the rails with lots of conversation turns or long contexts. Like when they need to remember a lot of vending machine conversation I guess.
A more objective look: https://arxiv.org/abs/2505.06120v1
https://github.com/NVIDIA/RULER
Gemini is much better. TBH the only models I’ve seen that are half decent at this are:
“Alternate attention” models like Gemini, Jamba Large or Falcon H1, depending on the iteration. Some recent versions of Gemini kinda lose this, then get it back.
Models finetuned specifically for this, like roleplay models or the Samantha model trained on therapy-style chat.
But most models are overtuned for oneshots like fix this table or write me a function, and don’t invest much in long context performance because it’s not very flashy.