Loading comparison…
HEAD TO HEAD
Yuichi Tateno (hotchpotch): bekko-system-one and Convai Innovations: laya-multilingual-noulxp, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | hotchpotch/bekko-system-one | convai-innovations/laya-multilingual-noulxp |
|---|---|---|
| Summary | Ultra-small English encoders (17M, 68M and 395M) fine-tuned from Ettin rerankers. Each answers choice, noul and score questions with a probability per candidate and no generated text. Experimental v0 by one developer; the weights have no licence assigned yet. | 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. |
| Decides | choice, noul, score | choice, score, noul, classify, route |
| Architecture | bekko | laya |
| Fine-tuned from | cross-encoder/ettin-reranker-400m-v1 | convai-innovations/laya |
| License | Unassigned: the weights licence is not finalised (treated as non-commercial); training code MIT | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | — |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 5 ms | 44.9 ms |
| p95 latency | 5.4 ms | 742 ms |
| Evaluation suite | The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026) | Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342 |
| Latest version | 2026.09 | 0.1.0 |
| Variants | 0_BekkoInference | noulxp |
| Size of latest version | 1.5 GB | 648.9 MB |
| Files | 9 | 9 |
| Downloads | 0 | 29 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, ettin, onnx, browser, small, 395m | noulxp, unofficial, onnx, fp32-o23, encoder, mmbert, multilingual, rlcd |
| Updated | Oct 7, 2026 | Oct 24, 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.
bekko-system-one is from Yuichi Tateno (hotchpotch) and laya-multilingual-noulxp from Convai Innovations. Both have open weights you can download and run. Both answer choice, noul and score questions. Only laya-multilingual-noulxp answers classify and route. laya-multilingual-noulxp is the smaller model, at 322M parameters to 395M. bekko-system-one is licensed other; laya-multilingual-noulxp, apache-2.0.
Neither publishes an accuracy figure. Test both on your own labelled examples.
bekko-system-one: Free (open weights). laya-multilingual-noulxp: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, bekko-system-one answers in about 5 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 hotchpotch/bekko-system-one and systemone pull convai-innovations/laya-multilingual-noulxp download the weights.