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.
The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
decision
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-9b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
77.4%
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 decision?
clm is from Contrastive-LM and decision from vLLM Semantic Router. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only clm answers rank. clm is the smaller model, at 8.0B parameters to 9.0B.
Which is more accurate, clm or decision?
Only decision publishes an accuracy figure (77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted)); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or decision?
clm: Free (open weights). decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or decision locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull vllm-semantic-router/decision download the weights.
