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.
Metask Lab's calibrated decision model in 16 languages. Qwen3.5-4B with a merged LoRA trained with the Nimble candidate-logit objective; one forward pass and a softmax over at most 26 answer-letter logits, with one temperature per question type.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
metask-jev
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
80.1%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
62.8 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 metask-jev?
clm is from Contrastive-LM and metask-jev from Metask Lab. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only clm answers rank. metask-jev is the smaller model, at 4.5B parameters to 8.0B.
Which is more accurate, clm or metask-jev?
Only metask-jev publishes an accuracy figure (80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or metask-jev?
clm: Free (open weights). metask-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or metask-jev locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull metask-lab/metask-jev download the weights.
Evaluation suite
—
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
