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.
TokenRhythm's prefill-only decision model for agent workflows. Built on its NeoHorse-1-4B (a Qwen3.5-4B derivative), it predicts Choice, Noul and Score answers over application-defined options without generating text, with optional single-image input.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
ajev
neohorse
Fine-tuned from
google/gemma-4-26b-a4b-it
tokenrhythm/neohorse-1-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
75.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
49 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 neohorse-jev?
ajev is from Andy Zhang and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, score and noul questions. Only neohorse-jev answers classify and route. neohorse-jev is the smaller model, at 4.0B parameters to 26B.
Which is more accurate, ajev or neohorse-jev?
Only neohorse-jev publishes an accuracy figure (75.3% on JevBench public set (231 items), vLLM, maker's run); ajev does not, so there is no comparison to make without your own test.
Which is cheaper, ajev or neohorse-jev?
ajev: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run ajev or neohorse-jev locally?
Yes, both: systemone pull andy-zhang/ajev and systemone pull tokenrhythm/neohorse-jev download the weights.
—
Evaluation suite
Sequential requests, the maker's own measurement
JevBench public set (231 items), vLLM, maker's run
