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.
A typed-decision layer for Google's DiffusionGemma, from David Villalón at Maisa AI. It compiles a request into a small answer canvas, runs one denoising read on patched vLLM and reads the probabilities of the allowed labels, for text, images and images offered as options.
Decides
choice, score, noul, rank, classify, route
choice, score, noul
Architecture
clm
djev
Fine-tuned from
qwen/qwen3-8b
google/diffusiongemma-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Maisa
Input price
—
$0.035/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 djev?
clm is from Contrastive-LM and djev from Maisa. clm has open weights you can download and run; djev has open weights and a hosted API. Both answer choice, score and noul questions. Only clm answers rank, classify and route. clm is the smaller model, at 8.0B parameters to 26B.
Which is more accurate, clm or djev?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, clm or djev?
clm: Free (open weights). djev: $0.035 / $0 per 1M, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run clm or djev locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull maisa/djev download the weights.
