HEAD TO HEAD
Contrastive-LM: clm and Maziyar Panahi: modernjev-decide, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | contrastive-lm/clm | maziyar-panahi/modernjev-decide |
|---|---|---|
| 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 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated. |
| Decides | choice, score, noul, rank, classify, route | choice, rank, route |
| Architecture | clm | modernjev |
| Fine-tuned from | qwen/qwen3-8b | answerdotai/modernbert-base |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 73.4% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | — | AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) |
| Latest version | 2026.09.25 | 2026.09 |
| Variants | LICENSE | — |
| Size of latest version | 72.1 MB | 574.1 MB |
| Files | 3 | 5 |
| Downloads | 45 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, contrastive, qwen, ranking, 8b | system-one, encoder, modernbert, cross-encoder, tool-routing, preview, 149.6m |
| Updated | Nov 21, 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 modernjev-decide from Maziyar Panahi. Both have open weights you can download and run. Both answer choice, rank and route questions. Only clm answers score, noul and classify. modernjev-decide is the smaller model, at 150M parameters to 8.0B.
Only modernjev-decide publishes an accuracy figure (73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)); clm does not, so there is no comparison to make without your own test.
clm: Free (open weights). modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull contrastive-lm/clm and systemone pull maziyar-panahi/modernjev-decide download the weights.