CLM
Contrastive Language Models (CLMs) are a new class of System One model trained with a contrastive learning objective that connects states and actions.
CLM launched on 23 September 2026. It ranked #89 on Daily Launch on 14 October 2026 with a Launch Score of 33, from 3k stars in 20 days on GitHub. It was new in the ranking that day.
What is CLM?
We invite the community to plug it into their own agents and benchmarks! States longer than 2048 tokens are truncated. For longer states, raise both limits together, e.g. --max-model-len 8192 on vllm serve and clm-serve --max-tokens 8192 (needs more GPU memory).
From its README on GitHub
CLM is a repo by Contrastive-LM on GitHub. It is written in Python and released under the Apache-2.0 license.
How to get CLM
pip install contrastive-lmFrom its README on GitHub
More steps and the source are in its repository on GitHub.
Launch timeline
Launch Score, last 7 days
Ranked on one day so far: 33 of 100 on 14 October.