HEAD TO HEAD
Convai Innovations: laya 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 | kotoba-labs/open-jev-deberta-v3-large |
|---|---|---|
| Summary | An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU. | 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 | answerdotai/modernbert-large | 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 | 39.5 ms | 28 ms |
| p95 latency | — | — |
| Evaluation suite | — | Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) |
| Latest version | 2026.09.25 | 2026.09 |
| Variants | multilingual, tokenizer, eval, typed-decisions, encoder | — |
| Size of latest version | 2.2 GB | 1.6 GB |
| Files | 19 | 9 |
| Downloads | 419 | 2 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, modernbert, rlcd, multilingual, 421m | system-one, encoder, deberta, public-data, 434m |
| Updated | Nov 19, 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 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 answers route. laya is the smaller model, at 421M 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 does not, so there is no comparison to make without your own test.
laya: 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 in about 39.5 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull convai-innovations/laya and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.