HEAD TO HEAD
Convai Innovations: laya and SAGEA: mira, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | convai-innovations/laya | sagea/mira |
|---|---|---|
| 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. | Small open typed-decision model with calibrated probabilities, first-class Nepali coverage. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | laya | mira |
| Fine-tuned from | answerdotai/modernbert-large | jhu-clsp/mmbert-small |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 61.3% |
| Calibration error | — | 0.083 |
| Valid action rate | — | 100.0% |
| Median latency | 39.5 ms | 30 ms |
| p95 latency | — | 43 ms |
| Evaluation suite | — | s1-decision-bench |
| Latest version | 2026.09.25 | 0.1.5 |
| Variants | multilingual, tokenizer, eval, typed-decisions, encoder | — |
| Size of latest version | 2.2 GB | 568.8 MB |
| Files | 19 | 12 |
| Downloads | 419 | 209 |
| Stars | 0 | 1 |
| Tags | system-one, encoder, modernbert, rlcd, multilingual, 421m | routing, nepali, nepal, calibration, cpu |
| Updated | Nov 19, 2026 | Nov 18, 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 mira from SAGEA. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions.
Only mira publishes an accuracy figure (61.3% on s1-decision-bench); laya does not, so there is no comparison to make without your own test.
laya: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, mira answers in about 30 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 sagea/mira download the weights.