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.
Fastino's open-weight decision model. A DeBERTa-v3-large encoder that scores label sets supplied at runtime, answers single-label, multi-label, yes/no and ordinal questions in one pass, and extracts spans and relations.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, extract, route
Architecture
clm
gliner2
Fine-tuned from
qwen/qwen3-8b
fastino/gliner2-large-v1
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Fastino
Input price
—
—
Decision accuracy
—
60.2%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
38.3 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 gliner2-5-decide?
clm is from Contrastive-LM and gliner2-5-decide from Fastino Labs. clm has open weights you can download and run; gliner2-5-decide has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. Only clm answers rank. Only gliner2-5-decide answers extract. gliner2-5-decide is the smaller model, at 340M parameters to 8.0B.
Which is more accurate, clm or gliner2-5-decide?
Only gliner2-5-decide publishes an accuracy figure (60.2% on Fastino fast-decisions suite (17 datasets)); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or gliner2-5-decide?
clm: Free (open weights). gliner2-5-decide: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run clm or gliner2-5-decide locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull fastino-labs/gliner2-5-decide download the weights.
