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.
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.
Decides
choice, score, noul, classify
choice, score, noul, classify, route
Architecture
hopper
laya
Fine-tuned from
qwen/qwen3.5-4b
answerdotai/modernbert-large
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%
—
Calibration error
0.102
—
Valid action rate
—
—
Median latency
—
39.5 ms
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 laya?
hopper is from HopitAI and laya from Convai Innovations. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only laya answers route. laya is the smaller model, at 421M parameters to 4.0B. hopper is licensed other; laya, apache-2.0.
Which is more accurate, hopper or laya?
Only hopper publishes an accuracy figure (68.5% on JevBench public hard tier (111 items, measured by the authors)); laya does not, so there is no comparison to make without your own test.
Which is cheaper, hopper or laya?
hopper: Free (open weights). laya: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run hopper or laya locally?
Yes, both: systemone pull hopit-ai/hopper and systemone pull convai-innovations/laya download the weights.
—
Evaluation suite
JevBench public hard tier (111 items, measured by the authors)
