A 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.
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, rank, route
choice, score, noul, classify, route
Architecture
modernjev
neohorse
Fine-tuned from
answerdotai/modernbert-base
tokenrhythm/neohorse-1-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
73.4%
75.3%
Calibration error
—
—
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 modernjev-decide and neohorse-jev?
modernjev-decide is from Maziyar Panahi and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice and route questions. Only modernjev-decide answers rank. Only neohorse-jev answers score, noul and classify. modernjev-decide is the smaller model, at 150M parameters to 4.0B.
Which is more accurate, modernjev-decide or neohorse-jev?
They report on different suites — modernjev-decide 73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split), neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, modernjev-decide or neohorse-jev?
modernjev-decide: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run modernjev-decide or neohorse-jev locally?
Yes, both: systemone pull maziyar-panahi/modernjev-decide and systemone pull tokenrhythm/neohorse-jev download the weights.
—
—
Evaluation suite
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)
JevBench public set (231 items), vLLM, maker's run
