GLM-5.3-Flash is now the cheapest way to reach Artificial Analysis Intelligence Index 52.3 to 57.5, at 8.7¢ per task, and displaced Muse Spark 1.2, Grok 4.5, Gemini 3.7 Flash, and DeepSeek V4 Pro from the Pareto frontier.
Author here. I made these plots because I had been searching for them for months and never found quite what I wanted: how the cheapest way to reach a fixed capability level has moved over time. Artificial Analysis publishes enough data to reconstruct it. If someone knows of a source that already tracks this, with historical prices, please share.
It blows my mind how fast models are getting better and this is the first article I’ve seen that shows just that and leaves almost no room for disagreement. Well done.
I wonder if it might drive the point even further if the graph scales were linear? Or maybe the progress has been so great that this would make the graphs unreadable?
It looks like most of these magic mirrors have been done with an old android whereas this one uses a monitor and a rasberry pi. If I wanted to make one, which one should I choose. What are the pros and cons of this approach?
My thoughts as well. Maybe Uber and Lyft will migrate to this pricing model if it helps them get around these legal issues. Does anyone with legal knowledge know if this is a viable strategy?
advance card: https://catalystneuro.com/llm-cost-frontier/images/advances/...
tracker: https://catalystneuro.com/llm-cost-frontier/