Loading comparison…
HEAD TO HEAD
TextCortex: laya-cybersec and solvi: solvi, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | textcortex/laya-cybersec | solvi-ai/solvi |
|---|---|---|
| Summary | Laya fine-tune that scans untrusted text (extracted files, knowledge-base documents, agent skills, tool descriptions) for prompt injection and data exfiltration in English and German, as a noul question answered in one forward pass. 322M parameters, PyTorch and ONNX. | 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 | noul, classify | choice, score, noul, rank, extract |
| Architecture | laya | solvi |
| Fine-tuned from | convaiinnovations/laya-multilingual | answerdotai/modernbert-large |
| License | Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed | 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 | 95.4 ms | — |
| p95 latency | 149 ms | — |
| Evaluation suite | TextCortex saved run: 279 single-window inputs, PyTorch batch one | Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot |
| Latest version | 2026.10 | 2026.09 |
| Variants | encoder, onnx, tokenizer | onnx |
| Size of latest version | 1.8 GB | 2.2 GB |
| Files | 9 | 11 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, laya, encoder, prompt-injection, security, guardrails, multilingual, onnx, 322m | 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.
laya-cybersec is from TextCortex and solvi from solvi. Both have open weights you can download and run. Both answer noul questions. Only laya-cybersec answers classify. Only solvi answers choice, score, rank and extract. laya-cybersec reads up to 1K tokens of state, against 512 tokens for solvi. laya-cybersec is the smaller model, at 322M parameters to 396M. laya-cybersec is licensed other; solvi, apache-2.0.
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); laya-cybersec does not, so there is no comparison to make without your own test.
laya-cybersec: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull textcortex/laya-cybersec and systemone pull solvi-ai/solvi download the weights.