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.
Invergent's decision model for text and images. A fine-tune of Gemma-4-26B-A4B (about 4B parameters active per token) that answers Choice, Noul and Score questions, with an optional thinking mode for harder questions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
neohorse
rune
Fine-tuned from
tokenrhythm/neohorse-1-4b
google/gemma-4-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Invergent
Input price
—
—
Decision accuracy
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 neohorse-jev and rune?
neohorse-jev is from TokenRhythm and rune from Surogate (Invergent). neohorse-jev has open weights you can download and run; rune has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. neohorse-jev is the smaller model, at 4.0B parameters to 26B.
Which is more accurate, neohorse-jev or rune?
Only neohorse-jev publishes an accuracy figure (75.3% on JevBench public set (231 items), vLLM, maker's run); rune does not, so there is no comparison to make without your own test.
Which is cheaper, neohorse-jev or rune?
neohorse-jev: Free (open weights). rune: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run neohorse-jev or rune locally?
Yes, both: systemone pull tokenrhythm/neohorse-jev and systemone pull surogate/rune download the weights.
—
Evaluation suite
JevBench public set (231 items), vLLM, maker's run
