Metask Lab's calibrated decision model in 16 languages. Qwen3.5-4B with a merged LoRA trained with the Nimble candidate-logit objective; one forward pass and a softmax over at most 26 answer-letter logits, with one temperature per question type.
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.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
metask-jev
rizzo-flow
Fine-tuned from
qwen/qwen3.5-4b
xhtoken/spark-x2.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.1%
64.8%
Calibration error
—
0.112
Valid action rate
—
—
Median latency
62.8 ms
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 metask-jev and rizzo-flow?
metask-jev is from Metask Lab and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. rizzo-flow is the smaller model, at 4.0B parameters to 4.5B.
Which is more accurate, metask-jev or rizzo-flow?
They report on different suites — metask-jev 80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run, rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, metask-jev or rizzo-flow?
metask-jev: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, metask-jev or rizzo-flow?
By their publishers’ figures, metask-jev answers in about 62.8 ms at the median and rizzo-flow in about 195 ms — measured on different hardware, so treat it as a rough guide.
Can I run metask-jev or rizzo-flow locally?
Yes, both: systemone pull metask-lab/metask-jev and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
Evaluation suite
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
