All models
COMPARE
Put models side by side.
What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.
| Property | contrastive-lm/clm |
|---|---|
| Summary | 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. |
| Decides | choice, score, noul, rank, classify, route |
| Architecture | clm |
| Fine-tuned from | qwen/qwen3-8b |
| License | apache-2.0 |
| Availability | Open weights |
| Hosted by | — |
| Input price | — |
| Decision accuracy | — |
| Calibration error | — |
| Valid action rate | — |
| Median latency | — |
| p95 latency | — |
| Evaluation suite | — |
| Latest version | 2026.09.25 |
| Variants | LICENSE |
| Size of latest version | 72.1 MB |
| Files | 3 |
| Downloads | 0 |
| Stars | 0 |
| Tags | system-one, contrastive, qwen, ranking, 8b |
| Updated | Sep 25, 2026 |