> it shows how quickly you can go back and forth with a model

Another member of the pro-REPL / anti-agentic tribe. There are dozens of us!

Why does AA choose ~$3.1 per task to be the breaking point for "most attractive quadrant" highlight? Surely the most attractive section is just being close to the entire frontier?

It's a quarter of the graph (hence quadrant)

The choice of X-axis maximum and Y-axis maximum dictates the cutoff point of the quadrant. With a maximum of $80 per task, the quadrant is $3.1 and lower. If some new model gets released and costs more than $80 per task, the "most attractive" cutoff moves up from $3.1 since they have to move the X-axis max. It's completely arbitrary.

It's not saying that being inside that quadrant is a hard cut-off it's just illustrating the direction of the pareto frontier

It is suggesting a hard cutoff since it says "most" attractive, a superlative, instead of "more" attractive. And it is not pareto optimal, because if the models get really good and are scoring 10x more for 10x cheaper that green region will no longer be pareto optimal.

Of the 4 quadrants it is the most attractive

I suppose you’re not wrong lol

Note that the graph is misleading for open models since it's only measuring their official providers and that's rarely the fastest.

The official Moonshot provider for Kimi K3.1 Pro is currently dead last for speed on OpenRouter. You could run it more than 5x faster for the same cost somewhere else.

I'm really interested that Fable 5.2 Low seems to be a universal improvement in quality and time over Opus 5.5 Medium and High.

Certainly cost is a factor, but if your goal is quality and low latency at any token cost, it's now a fascinating option.