An open System One model from Interfaze AI. A rank-32 LoRA on Qwen3.5-4B reads yes/no, choice and score answers from the logits of one forward pass, returns calibrated probabilities and serves the /v1/systemone API.
A ModernBERT-large encoder with an option-marker head. Premise and options are packed into one sequence and each option's marker is scored in a single bidirectional pass; version 1.2 makes the scoring order-invariant.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
lev
von
Fine-tuned from
qwen/qwen3.5-4b
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
68.9%
63.9%
Calibration error
0.115
0.045
Valid action rate
—
—
Median latency
69 ms
18 ms
p95 latency
—
—
Evaluation suite
S1Bench (13 public subsets, macro)
JevBench public standard tier
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 lev and von?
lev is from Interfaze AI and von from wfzyx. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only lev answers route. von is the smaller model, at 395M parameters to 4.0B.
Which is more accurate, lev or von?
They report on different suites — lev 68.9% on S1Bench (13 public subsets, macro), von 63.9% on JevBench public standard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, lev or von?
lev: Free (open weights). von: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, lev or von?
By their publishers’ figures, von answers in about 18 ms at the median and lev in about 69 ms — measured on different hardware, so treat it as a rough guide.
Can I run lev or von locally?
Yes, both: systemone pull interfaze-ai/lev and systemone pull wfzyx/von download the weights.