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.
Invergent's decision model for text and images. A fine-tune of Gemma-4-26B-A4B (about 4B parameters active per token) that answers Choice, Noul and Score questions, with an optional thinking mode for harder questions.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
rune
Fine-tuned from
qwen/qwen3-8b
google/gemma-4-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Invergent
Input price
—
—
Decision accuracy
—
—
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 rune?
clm is from Contrastive-LM and rune from Surogate (Invergent). clm has open weights you can download and run; rune has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. Only clm answers rank. clm is the smaller model, at 8.0B parameters to 26B.
Which is more accurate, clm or rune?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, clm or rune?
clm: Free (open weights). rune: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run clm or rune locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull surogate/rune download the weights.
