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.
A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
bev-decider
julia
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%
73.2%
Calibration error
—
—
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 bev-decider and julia-1?
bev-decider is from Avishek Biswas and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice, score and noul questions. Only julia-1 answers classify and route. julia-1 reads up to 8K tokens of state, against 2K tokens for bev-decider. julia-1 is the smaller model, at 144M parameters to 478M. bev-decider is licensed cc-by-nc-4.0; julia-1, apache-2.0.
Which is more accurate, bev-decider or julia-1?
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, julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev-decider or julia-1?
bev-decider: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev-decider or julia-1 locally?
Yes, both: systemone pull avishek-biswas/bev-decider and systemone pull supersonic-labs/julia-1 download the weights.
Evaluation suite
avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own
typed-decisions test set (400 cases, 2,000 questions)
