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 Thai-and-English System One model. Qwen3.5-0.8B continued-pretrained on about 5B Thai tokens, its language-model head replaced by a 256-way slot head (slot 255 abstains), trained on 2–3M decision examples and temperature-calibrated per question type.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
openthai
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-0.8b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
74.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
40 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 openthai-systemone?
clm is from Contrastive-LM and openthai-systemone from iApp Technology. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only clm answers rank. openthai-systemone is the smaller model, at 800M parameters to 8.0B.
Which is more accurate, clm or openthai-systemone?
Only openthai-systemone publishes an accuracy figure (74.3% on Bespoke public subsets (13, macro average)); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or openthai-systemone?
clm: Free (open weights). openthai-systemone: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or openthai-systemone locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull iapp-technology/openthai-systemone download the weights.
