A 0.6B decision model on Qwen3-0.6B-Base from the DocsGPT team. Give it a state and typed questions (yes/no, a choice of up to 16 options, a 3- or 4-level score) and it returns calibrated probabilities in one pass, for RAG and agent checks.
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, rank, route
choice, score, noul, rank, extract
Architecture
arc-decide
solvi
Fine-tuned from
qwen/qwen3-0.6b-base
answerdotai/modernbert-large
License
mit
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
—
—
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 arc-decide and solvi?
arc-decide is from Arc53 and solvi from solvi. Both have open weights you can download and run. Both answer choice, score, noul and rank questions. Only arc-decide answers classify and route. Only solvi answers extract. solvi is the smaller model, at 396M parameters to 600M. arc-decide is licensed mit; solvi, apache-2.0.
Which is more accurate, arc-decide 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); arc-decide does not, so there is no comparison to make without your own test.
Which is cheaper, arc-decide or solvi?
arc-decide: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or solvi locally?
Yes, both: systemone pull arc53/arc-decide 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
