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.
A 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal.
Decides
choice, score, noul, classify, route
choice, score, noul, rank, extract
Architecture
laya
solvi
Fine-tuned from
answerdotai/modernbert-large
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
59.4%
Calibration error
—
0.210
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 laya and solvi?
laya is from Convai Innovations and solvi from solvi. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya answers classify and route. Only solvi answers rank and extract. solvi is the smaller model, at 396M parameters to 421M.
Which is more accurate, laya or solvi?
Only solvi publishes an accuracy figure (59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot); laya does not, so there is no comparison to make without your own test.
Which is cheaper, laya or solvi?
laya: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run laya or solvi locally?
Yes, both: systemone pull convai-innovations/laya and systemone pull solvi-ai/solvi download the weights.
—
Evaluation suite
—
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
