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.
StartLux's decision family in six sizes, 0.8B to a 35B-A3B mixture of experts. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server. Text, JSON or images, up to 256K tokens.
Decides
choice, score, noul, rank, extract
choice, score, noul
Architecture
solvi
startlux-decision
Fine-tuned from
answerdotai/modernbert-large
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
59.4%
88.3%
Calibration error
0.210
—
Valid action rate
—
—
Median latency
—
26 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 solvi and startlux-decision?
solvi is from solvi and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, score and noul questions. Only solvi answers rank and extract. startlux-decision reads up to 256K tokens of state, against 512 tokens for solvi. solvi is the smaller model, at 396M parameters to 4.7B. solvi is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, solvi or startlux-decision?
They report on different suites — solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot, startlux-decision 88.3% on JevBench public set (231 items; 204 correct), maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, solvi or startlux-decision?
solvi: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run solvi or startlux-decision locally?
Yes, both: systemone pull solvi-ai/solvi and systemone pull startlux/startlux-decision download the weights.
—
Evaluation suite
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
JevBench public set (231 items; 204 correct), maker's run
