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.
An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
bev-decider
laya
Fine-tuned from
qwen/qwen3-0.6b
answerdotai/modernbert-large
License
cc-by-nc-4.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
74.7%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
39.5 ms
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 laya?
bev-decider is from Avishek Biswas and laya from Convai Innovations. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya answers classify and route. bev-decider reads up to 2K tokens of state, against 512 tokens for laya. laya is the smaller model, at 421M parameters to 478M. bev-decider is licensed cc-by-nc-4.0; laya, apache-2.0.
Which is more accurate, bev-decider or laya?
Only bev-decider publishes an accuracy figure (74.7% on avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own); laya does not, so there is no comparison to make without your own test.
Which is cheaper, bev-decider or laya?
bev-decider: Free (open weights). laya: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev-decider or laya locally?
Yes, both: systemone pull avishek-biswas/bev-decider and systemone pull convai-innovations/laya download the weights.
—
Evaluation suite
avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own
