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 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.
Decides
choice, score, noul, classify, route
choice, rank, route
Architecture
julia
modernjev
Fine-tuned from
jhu-clsp/mmbert-small
answerdotai/modernbert-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
73.2%
73.4%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
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 modernjev-decide?
julia-1 is from Supersonic Labs and modernjev-decide from Maziyar Panahi. Both have open weights you can download and run. Both answer choice and route questions. Only julia-1 answers score, noul and classify. Only modernjev-decide answers rank. julia-1 reads up to 8K tokens of state, against 4K tokens for modernjev-decide. julia-1 is the smaller model, at 144M parameters to 150M.
Which is more accurate, julia-1 or modernjev-decide?
They report on different suites — julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions), modernjev-decide 73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, julia-1 or modernjev-decide?
julia-1: Free (open weights). modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run julia-1 or modernjev-decide locally?
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull maziyar-panahi/modernjev-decide download the weights.
—
Evaluation suite
typed-decisions test set (400 cases, 2,000 questions)
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)
