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 multimodal decision classifier over text, image, audio and video on Gemma 4 12B, fine-tuned on 30,000 questions. Returns a probability per option and generates nothing.
Decides
choice, score, noul, rank, classify, route
choice, noul, score, classify
Architecture
clm
jev-omni
Fine-tuned from
qwen/qwen3-8b
google/gemma-4-12b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
87.6%
Calibration error
—
0.040
Valid action rate
—
—
Median latency
—
83 ms
p95 latency
—
—
Evaluation suite
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 jev-omni?
clm is from Contrastive-LM and jev-omni from akhilaaa3. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only clm answers rank and route. clm is the smaller model, at 8.0B parameters to 12B.
Which is more accurate, clm or jev-omni?
Only jev-omni publishes an accuracy figure (87.6% on DecisionBench Medium (author's set)); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or jev-omni?
clm: Free (open weights). jev-omni: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or jev-omni locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull akhilaaa3/jev-omni download the weights.
