Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
A 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.
Decides
choice, score, noul, classify, route
choice, rank, route
Architecture
mira
modernjev
Fine-tuned from
jhu-clsp/mmbert-small
answerdotai/modernbert-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
61.3%
73.4%
Calibration error
0.083
—
Valid action rate
100.0%
—
Median latency
30 ms
—
p95 latency
43 ms
—
Evaluation suite
s1-decision-bench
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)
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 modernjev-decide?
mira is from SAGEA and modernjev-decide from Maziyar Panahi. Both have open weights you can download and run. Both answer choice and route questions. Only mira answers score, noul and classify. Only modernjev-decide answers rank.
Which is more accurate, mira or modernjev-decide?
They report on different suites — mira 61.3% on s1-decision-bench, modernjev-decide 73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, mira or modernjev-decide?
mira: Free (open weights). modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run mira or modernjev-decide locally?
Yes, both: systemone pull sagea/mira and systemone pull maziyar-panahi/modernjev-decide download the weights.
