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.
The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.
Decides
choice, score, noul, rank, classify, route
choice, score, noul, classify, route
Architecture
clm
decider
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-2b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
80.2%
Calibration error
—
0.038
Valid action rate
—
—
Median latency
—
3.2 ms
p95 latency
—
—
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 decider?
clm is from Contrastive-LM and decider from Mapika. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only clm answers rank. decider is the smaller model, at 2.0B parameters to 8.0B.
Which is more accurate, clm or decider?
Only decider publishes an accuracy figure (80.2% on Decider 67-task regression set); clm does not, so there is no comparison to make without your own test.
Which is cheaper, clm or decider?
clm: Free (open weights). decider: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or decider locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull mapika/decider download the weights.
