Shanghai AI Laboratory's multimodal decision model. A fine-tune of Qwen3.5-4B's language backbone (vision tower frozen) that answers up to 16 Choice, Score and Noul questions about a state and up to eight images in one forward pass, with a fitted calibration temperature.
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, score, noul, classify, route
choice, score, noul, classify, route
Architecture
intern-decision
neohorse
Fine-tuned from
qwen/qwen3.5-4b
tokenrhythm/neohorse-1-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.6%
75.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
44 ms
—
p95 latency
44.6 ms
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 intern-decision and neohorse-jev?
intern-decision is from InternLM (Shanghai AI Laboratory) and neohorse-jev from TokenRhythm. 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 4.5B.
Which is more accurate, intern-decision or neohorse-jev?
They report on different suites — intern-decision 80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), 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, intern-decision or neohorse-jev?
intern-decision: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run intern-decision or neohorse-jev locally?
Yes, both: systemone pull internlm/intern-decision and systemone pull tokenrhythm/neohorse-jev download the weights.
—
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)
JevBench public set (231 items), vLLM, maker's run
