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.
A 4B decision model fine-tuned from Qwen3.5-4B-Base. A state and typed questions (choice, yes/no, score) go in; a temperature-calibrated probability for every option comes out of one pass, through a self-hosted /v1/systemone-compatible server. Apache-2.0 weights and code.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
julia
wald
Fine-tuned from
jhu-clsp/mmbert-small
qwen/qwen3.5-4b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
73.2%
88.3%
Calibration error
—
0.045
Valid action rate
—
—
Median latency
—
33 ms
p95 latency
—
168 ms
Evaluation suite
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 wald?
julia-1 is from Supersonic Labs and wald from ORG2 AI. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. wald reads up to 128K tokens of state, against 8K tokens for julia-1. julia-1 is the smaller model, at 144M parameters to 4.2B.
Which is more accurate, julia-1 or wald?
They report on different suites — julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions), wald 88.3% on JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, julia-1 or wald?
julia-1: Free (open weights). wald: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run julia-1 or wald locally?
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull org2ai/wald download the weights.
typed-decisions test set (400 cases, 2,000 questions)
JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard
