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.
Juspay's open decision model. Qwen3.6-35B-A3B with a merged rank-16 LoRA, shipped with a pinned SGLang serving bundle that answers Choice, Score and Noul questions over text, images or a video through a TypeSafe-compatible /v1/systemone API.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
neohorse
xor
Fine-tuned from
tokenrhythm/neohorse-1-4b
qwen/qwen3.6-35b-a3b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
75.3%
90.0%
Calibration error
—
0.073
Valid action rate
—
—
Median latency
—
69 ms
p95 latency
—
162 ms
Evaluation suite
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 xor?
neohorse-jev is from TokenRhythm and xor from Juspay. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. neohorse-jev is the smaller model, at 4.0B parameters to 35B.
Which is more accurate, neohorse-jev or xor?
They report on different suites — neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run, xor 90.0% on JevBench public set (231 items), maker's self-run of Xor 1.2 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, neohorse-jev or xor?
neohorse-jev: Free (open weights). xor: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run neohorse-jev or xor locally?
Yes, both: systemone pull tokenrhythm/neohorse-jev and systemone pull juspay/xor download the weights.
JevBench public set (231 items), vLLM, maker's run
JevBench public set (231 items), maker's self-run of Xor 1.2
