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.
The first System One model. Reads a state, answers typed Choice, Score and Noul questions in one call with calibrated probabilities, and generates no text. Closed weights, served by TypeSafe AI.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
decider
jev
Fine-tuned from
qwen/qwen3.5-2b-base
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
TypeSafe AI
Input price
—
$0.042/MTok
Decision accuracy
80.2%
—
Calibration error
0.038
—
Valid action rate
—
—
Median latency
3.2 ms
—
p95 latency
—
—
Evaluation suite
Decider 67-task regression set
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 jev?
decider is from Mapika and jev from TypeSafe AI. decider has open weights you can download and run; jev is only available as a hosted API. Both answer choice, score, noul, classify and route questions. decider is licensed apache-2.0; jev, proprietary.
Which is more accurate, decider or jev?
Only decider publishes an accuracy figure (80.2% on Decider 67-task regression set); jev does not, so there is no comparison to make without your own test.
Which is cheaper, decider or jev?
decider: Free (open weights). jev: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run decider or jev locally?
decider yes — systemone pull mapika/decider downloads its weights. The other is only served as a hosted API.
