A 0.6B decision model on Qwen3-0.6B-Base from the DocsGPT team. Give it a state and typed questions (yes/no, a choice of up to 16 options, a 3- or 4-level score) and it returns calibrated probabilities in one pass, for RAG and agent checks.
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.
Decides
choice, score, noul, classify, rank, route
choice, score, noul, rank, classify, route
Architecture
arc-decide
clm
Fine-tuned from
qwen/qwen3-0.6b-base
qwen/qwen3-8b
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
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 arc-decide and clm?
arc-decide is from Arc53 and clm from Contrastive-LM. Both have open weights you can download and run. Both answer choice, score, noul, classify, rank and route questions. arc-decide is the smaller model, at 600M parameters to 8.0B. arc-decide is licensed mit; clm, apache-2.0.
Which is more accurate, arc-decide or clm?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, arc-decide or clm?
arc-decide: Free (open weights). clm: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or clm locally?
Yes, both: systemone pull arc53/arc-decide and systemone pull contrastive-lm/clm download the weights.
