Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
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
mira
solvi
Fine-tuned from
jhu-clsp/mmbert-small
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
61.3%
59.4%
Calibration error
0.083
0.210
Valid action rate
100.0%
—
Median latency
30 ms
—
p95 latency
43 ms
—
Evaluation suite
s1-decision-bench
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
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 mira and solvi?
mira is from SAGEA and solvi from solvi. Both have open weights you can download and run. Both answer choice, score and noul questions. Only mira answers classify and route. Only solvi answers rank and extract.
Which is more accurate, mira or solvi?
They report on different suites — mira 61.3% on s1-decision-bench, solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, mira or solvi?
mira: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run mira or solvi locally?
Yes, both: systemone pull sagea/mira and systemone pull solvi-ai/solvi download the weights.
