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.
Respan's behaviour-scoring model for evals, guardrails and monitoring. For each plain-language behaviour you define, it reads a conversation or agent trace and returns the probability the behaviour is present, absent or not observable, in one forward pass.
Decides
choice, score, noul, rank, classify, route
noul, classify
Architecture
clm
span
Fine-tuned from
qwen/qwen3-8b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Respan
Input price
—
$0.020/MTok
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 clm and span-01?
clm is from Contrastive-LM and span-01 from Respan. clm has open weights you can download and run; span-01 is only available as a hosted API. Both answer noul and classify questions. Only clm answers choice, score, rank and route. clm is licensed apache-2.0; span-01, proprietary.
Which is more accurate, clm or span-01?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, clm or span-01?
clm: Free (open weights). span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run clm or span-01 locally?
clm yes — systemone pull contrastive-lm/clm downloads its weights. The other is only served as a hosted API.
