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.
Juspay's open decision model. Qwen3.6-35B-A3B with a merged rank-16 LoRA, shipped with a pinned SGLang serving bundle that answers Choice, Score and Noul questions over text, images or a video through a TypeSafe-compatible /v1/systemone API.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
julia
xor
Fine-tuned from
jhu-clsp/mmbert-small
qwen/qwen3.6-35b-a3b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
73.2%
90.0%
Calibration error
—
0.073
Valid action rate
—
—
Median latency
—
69 ms
p95 latency
—
162 ms
Evaluation suite
typed-decisions test set (400 cases, 2,000 questions)
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 xor?
julia-1 is from Supersonic Labs and xor from Juspay. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. julia-1 is the smaller model, at 144M parameters to 35B.
Which is more accurate, julia-1 or xor?
They report on different suites — julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions), xor 90.0% on JevBench public set (231 items), maker's self-run of Xor 1.2 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, julia-1 or xor?
julia-1: Free (open weights). xor: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run julia-1 or xor locally?
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull juspay/xor download the weights.
JevBench public set (231 items), maker's self-run of Xor 1.2
