Loading comparison…
COMPARE
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 | mapika/decider |
|---|---|---|
| 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. | 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 | — | Decider 67-task regression set |
| Latest version | 2026.09.25 | 2026.09 |
| Variants | LICENSE | — |
| Size of latest version | 72.1 MB | 3.5 GB |
| Files | 3 | 4 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, contrastive, qwen, ranking, 8b | system-one, qwen, rl, calibrated, 2b |
| Updated | Sep 26, 2026 | Sep 26, 2026 |