Theo Browne argues that a single AI model tier list is inherently reductive because model quality depends on the task. He compares models using code quality, output-token efficiency, speed, cost, vision support and how reliably they follow instructions in real development workflows.
Theo Browne places Fable 5 alone at the top for code he is willing to merge, with OpenAI 5.6 Soul close behind as a more controllable and token-efficient general workhorse. He rates OpenAI 5.6 Luna highly for inexpensive structured tasks, while Kimi K3 and DeepSeek V4 Flash remain strong open-weight options with different tradeoffs.
Theo Browne is more critical of expensive or inefficient models, particularly those without vision or with unpredictable reasoning costs. His final ranking favors models that produce useful work with fewer tokens and less supervision, rather than those that lead on isolated benchmarks or raw generation speed.
Watch on YouTube