A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
FLock.io's typed-decision model, fine-tuned from Mapika's decider-2b. Reads one hidden state per question and scores the declared options, so an answer outside the list cannot occur; several questions about one state share a forward pass.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
julia
this-that
Fine-tuned from
jhu-clsp/mmbert-small
mapika/decider
License
apache-2.0
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
73.2%
87.8%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
31.4 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 julia-1 and this-that-model?
julia-1 is from Supersonic Labs and this-that-model from FLock.io. Both have open weights you can download and run. Both answer choice, score and noul questions. Only julia-1 answers classify and route. julia-1 is the smaller model, at 144M parameters to 1.9B. julia-1 is licensed apache-2.0; this-that-model, mit.
Which is more accurate, julia-1 or this-that-model?
They report on different suites — julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions), this-that-model 87.8% on limberc/this-that-complex-decisions (1,710 questions, FLock's benchmark) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, julia-1 or this-that-model?
julia-1: Free (open weights). this-that-model: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run julia-1 or this-that-model locally?
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull flock-io/this-that-model download the weights.
Evaluation suite
typed-decisions test set (400 cases, 2,000 questions)
