A 0.4B decision model made from the first 20 layers of Qwen3-0.6B plus a small attention head that compares options. It answers choice, noul and score questions in one pass, and choice order cannot change its answer by construction. Non-commercial licence.
Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
bev-decider
mira
Fine-tuned from
qwen/qwen3-0.6b
jhu-clsp/mmbert-small
License
cc-by-nc-4.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
74.7%
61.3%
Calibration error
—
0.083
Valid action rate
—
100.0%
Median latency
—
30 ms
p95 latency
—
43 ms
Evaluation suite
avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own
s1-decision-bench
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 bev-decider and mira?
bev-decider is from Avishek Biswas and mira from SAGEA. Both have open weights you can download and run. Both answer choice, score and noul questions. Only mira answers classify and route. bev-decider is licensed cc-by-nc-4.0; mira, apache-2.0.
Which is more accurate, bev-decider or mira?
They report on different suites — bev-decider 74.7% on avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own, mira 61.3% on s1-decision-bench — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev-decider or mira?
bev-decider: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev-decider or mira locally?
Yes, both: systemone pull avishek-biswas/bev-decider and systemone pull sagea/mira download the weights.
