The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.
A ModernBERT-large encoder with an option-marker head. Premise and options are packed into one sequence and each option's marker is scored in a single bidirectional pass; version 1.2 makes the scoring order-invariant.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
decider
von
Fine-tuned from
qwen/qwen3.5-2b-base
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.2%
63.9%
Calibration error
0.038
0.045
Valid action rate
—
—
Median latency
3.2 ms
18 ms
p95 latency
—
—
Evaluation suite
Decider 67-task regression set
JevBench public standard tier
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 decider and von?
decider is from Mapika and von from wfzyx. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only decider answers route. von is the smaller model, at 395M parameters to 2.0B.
Which is more accurate, decider or von?
They report on different suites — decider 80.2% on Decider 67-task regression set, von 63.9% on JevBench public standard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decider or von?
decider: Free (open weights). von: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, decider or von?
By their publishers’ figures, decider answers in about 3.2 ms at the median and von in about 18 ms — measured on different hardware, so treat it as a rough guide.
Can I run decider or von locally?
Yes, both: systemone pull mapika/decider and systemone pull wfzyx/von download the weights.