Loading comparison…
HEAD TO HEAD
Yuichi Tateno (hotchpotch): bekko-system-one and SAGEA: mira, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | hotchpotch/bekko-system-one | sagea/mira |
|---|---|---|
| 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. | Small open typed-decision model with calibrated probabilities, first-class Nepali coverage. |
| Decides | choice, noul, score | choice, score, noul, classify, route |
| Architecture | bekko | mira |
| Fine-tuned from | cross-encoder/ettin-reranker-400m-v1 | jhu-clsp/mmbert-small |
| 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 | — | 61.3% |
| Calibration error | — | 0.083 |
| Valid action rate | — | 100.0% |
| Median latency | 5 ms | 30 ms |
| p95 latency | 5.4 ms | 43 ms |
| Evaluation suite | The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026) | s1-decision-bench |
| Latest version | 2026.09 | 0.1.5 |
| Variants | 0_BekkoInference | — |
| Size of latest version | 1.5 GB | 568.8 MB |
| Files | 9 | 12 |
| Downloads | 0 | 112 |
| Stars | 0 | 1 |
| Tags | system-one, encoder, ettin, onnx, browser, small, 395m | routing, nepali, nepal, calibration, cpu |
| Updated | Oct 7, 2026 | Oct 6, 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 mira from SAGEA. Both have open weights you can download and run. Both answer choice, noul and score questions. Only mira answers classify and route. bekko-system-one is licensed other; mira, apache-2.0.
Only mira publishes an accuracy figure (61.3% on s1-decision-bench); bekko-system-one does not, so there is no comparison to make without your own test.
bekko-system-one: Free (open weights). mira: 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 mira in about 30 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull hotchpotch/bekko-system-one and systemone pull sagea/mira download the weights.