An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU.
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.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
laya
lev
Fine-tuned from
answerdotai/modernbert-large
qwen/qwen3.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
68.9%
Calibration error
—
0.115
Valid action rate
—
—
Median latency
39.5 ms
69 ms
p95 latency
—
—
Evaluation suite
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 laya and lev?
laya is from Convai Innovations and lev from Interfaze AI. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. laya is the smaller model, at 421M parameters to 4.0B.
Which is more accurate, laya or lev?
Only lev publishes an accuracy figure (68.9% on S1Bench (13 public subsets, macro)); laya does not, so there is no comparison to make without your own test.
Which is cheaper, laya or lev?
laya: Free (open weights). lev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, laya or lev?
By their publishers’ figures, laya answers in about 39.5 ms at the median and lev in about 69 ms — measured on different hardware, so treat it as a rough guide.
Can I run laya or lev locally?
Yes, both: systemone pull convai-innovations/laya and systemone pull interfaze-ai/lev download the weights.
