A rank-16 LoRA on Qwen3.5-4B built for the JevBench setting. A document, a policy and a question go in; a calibrated distribution over the option letters comes out of one forward pass. Research and demo use only.
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.
Decides
choice, score, noul, classify
choice, score, noul, classify, route
Architecture
hopper
julia
Fine-tuned from
qwen/qwen3.5-4b
jhu-clsp/mmbert-small
License
Research and demo use only (training data includes RACE, non-commercial); serving code Apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
68.5%
73.2%
Calibration error
0.102
—
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 hopper and julia-1?
hopper is from HopitAI and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only julia-1 answers route. julia-1 is the smaller model, at 144M parameters to 4.0B. hopper is licensed other; julia-1, apache-2.0.
Which is more accurate, hopper or julia-1?
They report on different suites — hopper 68.5% on JevBench public hard tier (111 items, measured by the authors), julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, hopper or julia-1?
hopper: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run hopper or julia-1 locally?
Yes, both: systemone pull hopit-ai/hopper and systemone pull supersonic-labs/julia-1 download the weights.
Evaluation suite
JevBench public hard tier (111 items, measured by the authors)
typed-decisions test set (400 cases, 2,000 questions)
