Loading comparison…
HEAD TO HEAD
Contrastive-LM: clm and solvi: solvi, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | contrastive-lm/clm | solvi-ai/solvi |
|---|---|---|
| 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. | A 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal. |
| Decides | choice, score, noul, rank, classify, route | choice, score, noul, rank, extract |
| Architecture | clm | solvi |
| Fine-tuned from | qwen/qwen3-8b | answerdotai/modernbert-large |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 59.4% |
| Calibration error | — | 0.210 |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | — | Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot |
| Latest version | 2026.09.25 | 2026.09 |
| Variants | LICENSE | onnx |
| Size of latest version | 72.1 MB | 2.2 GB |
| Files | 3 | 11 |
| Downloads | 12 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, contrastive, qwen, ranking, 8b | system-one, modernbert, cross-encoder, onnx, evidence, escalation, 396m |
| Updated | Oct 7, 2026 | Oct 7, 2026 |
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.
clm is from Contrastive-LM and solvi from solvi. Both have open weights you can download and run. Both answer choice, score, noul and rank questions. Only clm answers classify and route. Only solvi answers extract. solvi is the smaller model, at 396M parameters to 8.0B.
Only solvi publishes an accuracy figure (59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot); clm does not, so there is no comparison to make without your own test.
clm: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull contrastive-lm/clm and systemone pull solvi-ai/solvi download the weights.