Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Best Decision Models That Run on a CPU

CPU-class decision models (encoders and small decoders, under about 1.5B parameters) run next to the data with no GPU. Models are ranked by their Full score on the Jev Decision Index, a third-party board of 37 benchmarks with private held-out sets, until scores from our own Metatext Decision Benchmark are published. Latency is the board's median per call on its GPU runner.

Ranked list

No models match this ranking yet. The data is being populated and this page will fill in automatically.

Scores, calibration (ECE) and latency from the Jev Decision Index; cost per 1,000 decisions at 200 input tokens each. Updated daily.

More decision-model rankings

Best decision modelBest calibratedCheapestOpen weightsJev alternatives

Frequently asked questions

What is the best decision model that runs on a CPU?

CPU-class decision models are being loaded; this ranking fills in once they are.

How accurate are CPU decision models compared with large ones?

They trail the 27B-class leaders by a wide margin on the Decision Index, but answer in milliseconds on commodity hardware, which suits high-volume routing and filtering.