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.
Typed decisions from Google's frozen Gemma-4-12B-it, with no fine-tuning. A small shim over unmodified vLLM letters the options, reads the model's own probability for each letter at one answer position and applies one calibration temperature; one output token per decision.
Decides
choice, score, noul, rank, classify, route
choice, score, noul
Architecture
clm
cygnet
Fine-tuned from
qwen/qwen3-8b
google/gemma-4-12b-it
License
apache-2.0
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
87.9%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
50 ms
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 cygnet?
clm is from Contrastive-LM and cygnet from Blockbrain Labs. Both have open weights you can download and run. Both answer choice, score and noul questions. Only clm answers rank, classify and route. clm is the smaller model, at 8.0B parameters to 12B. clm is licensed apache-2.0; cygnet, mit.
Which is more accurate, clm or cygnet?
Only cygnet publishes an accuracy figure (87.9% on JevBench public set (231 items), JevBench CLI); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or cygnet?
clm: Free (open weights). cygnet: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or cygnet locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull blockbrain-labs/cygnet download the weights.
