top | item 46978786

(no title)

data-ottawa | 18 days ago

Custom tool calling formats are iffy in my experience. The models are all reinforcement learned to follow specific ones, so it’s always a battle and feels to me like using the tool wrong.

Have you had good results with the other frontier models?

discuss

order

thegeomaster|18 days ago

Not the parent commenter, but in my testing, all recent Claudes (4.5 onward) and the Gemini 3 series have been pretty much flawless in custom tool call formats.

data-ottawa|18 days ago

Thanks.

I’ve tested local models from Qwen, GLM, and Devstral families.

pcwelder|17 days ago

All anthropic models. Gemini 2.5 pro and above. Gemini 3 flash is very good too.

GPT models can follow tool format correctly but don't keep on going.

Grok-4+ are decent but with issues in longer chats.

Kimi 2.5 has issues with it reverting to its RL tool format.