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.
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, classify, route
choice, score, noul, rank, extract
Architecture
neohorse
solvi
Fine-tuned from
tokenrhythm/neohorse-1-4b
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
75.3%
59.4%
Calibration error
—
0.210
Valid action rate
—
—
Median latency
—
—
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 neohorse-jev and solvi?
neohorse-jev is from TokenRhythm and solvi from solvi. Both have open weights you can download and run. Both answer choice, score and noul questions. Only neohorse-jev answers classify and route. Only solvi answers rank and extract. solvi is the smaller model, at 396M parameters to 4.0B.
Which is more accurate, neohorse-jev or solvi?
They report on different suites — neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run, solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, neohorse-jev or solvi?
neohorse-jev: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run neohorse-jev or solvi locally?
Yes, both: systemone pull tokenrhythm/neohorse-jev and systemone pull solvi-ai/solvi download the weights.
—
Evaluation suite
JevBench public set (231 items), vLLM, maker's run
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
