Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
Juspay's open decision model. Qwen3.6-35B-A3B with a merged rank-16 LoRA, shipped with a pinned SGLang serving bundle that answers Choice, Score and Noul questions over text, images or a video through a TypeSafe-compatible /v1/systemone API.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
mira
xor
Fine-tuned from
jhu-clsp/mmbert-small
qwen/qwen3.6-35b-a3b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
74.5%
90.0%
Calibration error
0.025
0.073
Valid action rate
100.0%
—
Median latency
30 ms
69 ms
p95 latency
43 ms
162 ms
Evaluation suite
s1-decision-bench
JevBench public set (231 items), maker's self-run of Xor 1.2
Latest version
0.1.4
1.2.0
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 xor?
mira is from SAGEA and xor from Juspay. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions.
Which is more accurate, mira or xor?
They report on different suites — mira 74.5% on s1-decision-bench, xor 90.0% on JevBench public set (231 items), maker's self-run of Xor 1.2 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, mira or xor?
mira: Free (open weights). xor: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, mira or xor?
By their publishers’ figures, mira answers in about 30 ms at the median and xor in about 69 ms — measured on different hardware, so treat it as a rough guide.
Can I run mira or xor locally?
Yes, both: systemone pull sagea/mira and systemone pull juspay/xor download the weights.
