Contrastive Language Models score a state against a set of candidate actions with a contrastive objective. Two projection heads on frozen Qwen3-8B embeddings, trained with InfoNCE; clm-serve maps Choice, Score and Noul onto candidate ranking.
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, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
neohorse
Fine-tuned from
qwen/qwen3-8b
tokenrhythm/neohorse-1-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
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 clm and neohorse-jev?
clm is from Contrastive-LM and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only clm answers rank. neohorse-jev is the smaller model, at 4.0B parameters to 8.0B.
Which is more accurate, clm or neohorse-jev?
Only neohorse-jev publishes an accuracy figure (75.3% on JevBench public set (231 items), vLLM, maker's run); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or neohorse-jev?
clm: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or neohorse-jev locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull tokenrhythm/neohorse-jev download the weights.
—
Evaluation suite
—
JevBench public set (231 items), vLLM, maker's run
