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.
One of the earliest Jev-shaped scorers. A sequence-classification head on Qwen3.5-4B-Base scores each (state, question, option) triple and softmaxes per question. Non-commercial licence.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
jev
scorer
Fine-tuned from
—
qwen/qwen3.5-4b-base
License
proprietary
cc-by-nc-4.0
Availability
Hosted API
Open weights
Hosted by
TypeSafe AI
—
Input price
$0.042/MTok
—
Decision accuracy
—
70.7%
Calibration error
—
0.044
Valid action rate
—
—
Median latency
—
112 ms
p95 latency
—
—
Evaluation suite
—
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 jev and system-one-qwen3-5-4b-scorer?
jev is from TypeSafe AI and system-one-qwen3-5-4b-scorer from pngwn. jev is only available as a hosted API; system-one-qwen3-5-4b-scorer has open weights you can download and run. Both answer choice, score, noul and classify questions. Only jev answers route. jev is licensed proprietary; system-one-qwen3-5-4b-scorer, cc-by-nc-4.0.
Which is more accurate, jev or system-one-qwen3-5-4b-scorer?
Only system-one-qwen3-5-4b-scorer publishes an accuracy figure (70.7% on author-reported); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or system-one-qwen3-5-4b-scorer?
jev: $0.042 / $0 per 1M. system-one-qwen3-5-4b-scorer: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or system-one-qwen3-5-4b-scorer locally?
system-one-qwen3-5-4b-scorer yes — systemone pull pngwn/system-one-qwen3-5-4b-scorer downloads its weights. The other is only served as a hosted API.
