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 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.
Decides
choice, score, noul, rank, classify, route
choice, rank, route
Architecture
clm
modernjev
Fine-tuned from
qwen/qwen3-8b
answerdotai/modernbert-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
73.4%
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 modernjev-decide?
clm is from Contrastive-LM and modernjev-decide from Maziyar Panahi. Both have open weights you can download and run. Both answer choice, rank and route questions. Only clm answers score, noul and classify. modernjev-decide is the smaller model, at 150M parameters to 8.0B.
Which is more accurate, clm or modernjev-decide?
Only modernjev-decide publishes an accuracy figure (73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or modernjev-decide?
clm: Free (open weights). modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or modernjev-decide locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull maziyar-panahi/modernjev-decide download the weights.
—
Evaluation suite
—
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)
