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.
DecisionTune's 395M decision model: ModernBERT-large fine-tuned with a 4 KB scoring head that scores a marker per option, answering a choice or yes/no question in one encoder pass with a probability for every option. Runs locally on CPU or GPU via PyTorch, MLX or ONNX.
Decides
choice, score, noul
choice, noul, route, classify
Architecture
bev-decider
decisiontune
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
—
—
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 decisiontune?
bev-decider is from Avishek Biswas and decisiontune from DecisionTune. Both have open weights you can download and run. Both answer choice and noul questions. Only bev-decider answers score. Only decisiontune answers route and classify. decisiontune reads up to 8K tokens of state, against 2K tokens for bev-decider. decisiontune is the smaller model, at 395M parameters to 478M. bev-decider is licensed cc-by-nc-4.0; decisiontune, apache-2.0.
Which is more accurate, bev-decider or decisiontune?
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); decisiontune does not, so there is no comparison to make without your own test.
Which is cheaper, bev-decider or decisiontune?
bev-decider: Free (open weights). decisiontune: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev-decider or decisiontune locally?
Yes, both: systemone pull avishek-biswas/bev-decider and systemone pull decision-tune/decisiontune download the weights.
—
—
Evaluation suite
avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own
