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.
Juspay's open decision model. Qwen3.6-35B-A3B with a merged rank-16 LoRA, shipped with a pinned SGLang serving bundle that answers Choice, Score and Noul questions over text, images or a video through a TypeSafe-compatible /v1/systemone API.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
xor
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.6-35b-a3b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
90.0%
Calibration error
—
0.073
Valid action rate
—
—
Median latency
—
69 ms
p95 latency
—
162 ms
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 xor?
clm is from Contrastive-LM and xor from Juspay. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only clm answers rank. clm is the smaller model, at 8.0B parameters to 35B.
Which is more accurate, clm or xor?
Only xor publishes an accuracy figure (90.0% on JevBench public set (231 items), maker's self-run of Xor 1.2); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or xor?
clm: Free (open weights). xor: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or xor locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull juspay/xor download the weights.
—
JevBench public set (231 items), maker's self-run of Xor 1.2
