An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass.
French medical decision models by Bofeng Huang: pass a patient message or clinical note, a question and candidate answers, and get one probability per answer from a single forward pass. Choice, score and noul. A research model, not a medical device.
Decides
choice, score, noul
choice, score, noul
Architecture
ajev
docto-decision
Fine-tuned from
google/gemma-4-26b-a4b-it
qwen/qwen3.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
88.9%
Calibration error
—
0.079
Valid action rate
—
—
Median latency
49 ms
47 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 ajev and docto-decision?
ajev is from Andy Zhang and docto-decision from Bofeng Huang. Both have open weights you can download and run. Both answer choice, score and noul questions. docto-decision is the smaller model, at 4.7B parameters to 26B.
Which is more accurate, ajev or docto-decision?
Only docto-decision publishes an accuracy figure (88.9% on Docto Decision Bench fr v0.1 (12 tasks, mostly silver labels; the maker's own benchmark)); ajev does not, so there is no comparison to make without your own test.
Which is cheaper, ajev or docto-decision?
ajev: Free (open weights). docto-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, ajev or docto-decision?
By their publishers’ figures, docto-decision answers in about 47 ms at the median and ajev in about 49 ms — measured on different hardware, so treat it as a rough guide.
Can I run ajev or docto-decision locally?
Yes, both: systemone pull andy-zhang/ajev and systemone pull bofeng-huang/docto-decision download the weights.
Evaluation suite
Sequential requests, the maker's own measurement
Docto Decision Bench fr v0.1 (12 tasks, mostly silver labels; the maker's own benchmark)