HEAD TO HEAD
Convai Innovations: laya-multilingual-noulxp and Kotoba Labs: open-jev-deberta-v3-large, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | convai-innovations/laya-multilingual-noulxp | kotoba-labs/open-jev-deberta-v3-large |
|---|---|---|
| Summary | Unofficial NoulXP package of Convai Innovations' Laya multilingual (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations. | An independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify |
| Architecture | laya | open-jev |
| Fine-tuned from | convai-innovations/laya | microsoft/deberta-v3-large |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 85.4% |
| Calibration error | — | 0.022 |
| Valid action rate | — | — |
| Median latency | 44.9 ms | 28 ms |
| p95 latency | 742 ms | — |
| Evaluation suite | Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342 | Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) |
| Latest version | 0.1.0 | 2026.09 |
| Variants | noulxp | — |
| Size of latest version | 648.9 MB | 1.6 GB |
| Files | 9 | 9 |
| Downloads | 77 | 2 |
| Stars | 0 | 0 |
| Tags | noulxp, unofficial, onnx, fp32-o23, encoder, mmbert, multilingual, rlcd | system-one, encoder, deberta, public-data, 434m |
| Updated | Nov 22, 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-multilingual-noulxp is from Convai Innovations and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only laya-multilingual-noulxp answers route. laya-multilingual-noulxp reads up to 1K tokens of state, against 512 tokens for open-jev-deberta-v3-large. laya-multilingual-noulxp is the smaller model, at 322M parameters to 434M.
Only open-jev-deberta-v3-large publishes an accuracy figure (85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)); laya-multilingual-noulxp does not, so there is no comparison to make without your own test.
laya-multilingual-noulxp: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, open-jev-deberta-v3-large answers in about 28 ms at the median and laya-multilingual-noulxp in about 44.9 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull convai-innovations/laya-multilingual-noulxp and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.