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 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal.
Decides
choice, score, noul, classify, route
choice, score, noul, rank, extract
Architecture
julia
solvi
Fine-tuned from
jhu-clsp/mmbert-small
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
73.2%
59.4%
Calibration error
—
0.210
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 solvi?
julia-1 is from Supersonic Labs and solvi from solvi. Both have open weights you can download and run. Both answer choice, score and noul questions. Only julia-1 answers classify and route. Only solvi answers rank and extract. julia-1 reads up to 8K tokens of state, against 512 tokens for solvi. julia-1 is the smaller model, at 144M parameters to 396M.
Which is more accurate, julia-1 or solvi?
They report on different suites — julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions), solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, julia-1 or solvi?
julia-1: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run julia-1 or solvi locally?
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull solvi-ai/solvi download the weights.
Evaluation suite
typed-decisions test set (400 cases, 2,000 questions)
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
