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.
Invergent's decision model for text and images. A fine-tune of Gemma-4-26B-A4B (about 4B parameters active per token) that answers Choice, Noul and Score questions, with an optional thinking mode for harder questions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
julia
rune
Fine-tuned from
jhu-clsp/mmbert-small
google/gemma-4-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Invergent
Input price
—
—
Decision accuracy
73.2%
—
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 rune?
julia-1 is from Supersonic Labs and rune from Surogate (Invergent). julia-1 has open weights you can download and run; rune has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. rune reads up to 262K tokens of state, against 8K tokens for julia-1. julia-1 is the smaller model, at 144M parameters to 26B.
Which is more accurate, julia-1 or rune?
Only julia-1 publishes an accuracy figure (73.2% on typed-decisions test set (400 cases, 2,000 questions)); rune does not, so there is no comparison to make without your own test.
Which is cheaper, julia-1 or rune?
julia-1: Free (open weights). rune: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run julia-1 or rune locally?
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull surogate/rune download the weights.
Evaluation suite
typed-decisions test set (400 cases, 2,000 questions)
