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.
A 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal.
Decides
choice, score, noul
choice, score, noul, rank, extract
Architecture
ajev
solvi
Fine-tuned from
google/gemma-4-26b-a4b-it
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
59.4%
Calibration error
—
0.210
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 solvi?
ajev is from Andy Zhang and solvi from solvi. Both have open weights you can download and run. Both answer choice, score and noul questions. Only solvi answers rank and extract. solvi is the smaller model, at 396M parameters to 26B.
Which is more accurate, ajev or solvi?
Only solvi publishes an accuracy figure (59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot); ajev does not, so there is no comparison to make without your own test.
Which is cheaper, ajev or solvi?
ajev: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run ajev or solvi locally?
Yes, both: systemone pull andy-zhang/ajev and systemone pull solvi-ai/solvi download the weights.
Evaluation suite
Sequential requests, the maker's own measurement
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
