Haider.(@haider1):i wouldn't call fable 5.2 a benchmark-maxed model but it's not efficient than fable 5.1 as anthropic claims when the cost per task has doubled from 5.1 to 5.2 it feels more like a model with better post-training than fable 5.1 but only a smaller improvement over opus 5.5

Haider.

@haider1

open intelligence for a decentralized future

参加 November 2021

4.3K フォロー中 72.7K ファン

Haider.@haider1

2026.11.10 21:50

i wouldn't call fable 5.2 a benchmark-maxed model but it's not efficient than fable 5.1 as anthropic claims when the cost per task has doubled from 5.1 to 5.2 it feels more like a model with better post-training than fable 5.1 but only a smaller improvement over opus 5.5