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.
Superagent's 27B security decision model. It scores 2 to 16 supplied options in one forward pass and returns a probability for each, for triaging prompt injection, agent tool calls, code changes, logs and alerts. Apache-2.0 weights (gated, auto-approved) plus a hosted API.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
security-one
Fine-tuned from
qwen/qwen3-8b
denis-pplx/autojev-27b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Superagent
Input price
—
—
Decision accuracy
—
99.8%
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 security-one?
clm is from Contrastive-LM and security-one from Superagent. clm has open weights you can download and run; security-one has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. Only clm answers rank. clm is the smaller model, at 8.0B parameters to 27B.
Which is more accurate, clm or security-one?
Only security-one publishes an accuracy figure (99.8% on BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70)); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or security-one?
clm: Free (open weights). security-one: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run clm or security-one locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull superagent/security-one download the weights.
