Opus 5.5 is proof that we do need smarter models
Theo's take on Opus 5.5 and where smarter models matter; a practical builder-oriented model evaluation.
More in Models
20:58ModelsGPT-6.1 Terra vs Claude 5.5: Same Prompt, Not Even Close
GPT
Claudecomparison
6:26ModelsChina just dropped a new frontier model... and nobody can explain how
Fireshipfrontier model
18:32ModelsWhy Frontier Models Fail as Buy-Side Analysts - Janie Gu, Google DeepMind & Suyeol Yun, LinqAlpha
Google DeepMindevalsfinance
