Cool! It looks like Fable 5.2 (especially low and medium) also sit on the pareto frontier between time per task and intelligence: https://artificialanalysis.ai/models?speed=output-speed-over...

I am always interested in this comparison since it shows how quickly you can go back and forth with a model, capturing both tokens/task and tokens/second. The new models seem to be meaningfully better here.

▲

eli 12 minutes ago | parent | next [-]

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

For example, the official provider for Kimi K3.1 Pro is dead last for speed on OpenRouter. You could run it more than 5x faster for the same cost elsewhere, which should push it comfortably into the pareto quadrant.

▲

jrflo an hour ago | parent | prev | next [-]

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?

▲

StevenWaterman an hour ago | parent [-]

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

▲

jrflo 42 minutes ago | parent [-]

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.

	▲	StevenWaterman 30 minutes ago \| parent [-]
		It's not saying that being inside that quadrant is a hard cut-off it's just illustrating the direction of the pareto frontier If you take the average point inside the 4 quadrants, the top left one is pareto optimal (of the 4)

▲

jgalt212 an hour ago | parent | prev [-]

> 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!