A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
rizzo-flow
state-decider
Fine-tuned from
xhtoken/spark-x2.5-4b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
64.8%
76.8%
Calibration error
0.112
—
Valid action rate
—
—
Median latency
195 ms
—
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between rizzo-flow and state-decider-1?
rizzo-flow is from Rizzo AI Academy and state-decider-1 from meraGPT. rizzo-flow has open weights you can download and run; state-decider-1 is only available as a hosted API. Both answer choice, score, noul, classify and route questions. rizzo-flow is licensed apache-2.0; state-decider-1, proprietary.
Which is more accurate, rizzo-flow or state-decider-1?
They report on different suites — rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0, state-decider-1 76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, rizzo-flow or state-decider-1?
rizzo-flow: Free (open weights). state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run rizzo-flow or state-decider-1 locally?
rizzo-flow yes — systemone pull rizzo-ai-academy/rizzo-flow downloads its weights. The other is only served as a hosted API.
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
