HEAD TO HEAD
Mapika: decider and SAGEA: mira, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | mapika/decider | sagea/mira |
|---|---|---|
| Summary | A family of open System One models by Mark Marosi that softmax option-letter logits at an answer slot: decider-0.8b, 2b, 4b and 35b-a3b on Qwen3.5 bases, decider-12b on Gemma-4-12B-it, and training-free readouts of larger chat models. This page carries decider-2b v11. | Small open typed-decision model with calibrated probabilities, first-class Nepali coverage. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | decider | mira |
| Fine-tuned from | qwen/qwen3.5-2b-base | jhu-clsp/mmbert-small |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 75.2% | 61.3% |
| Calibration error | — | 0.083 |
| Valid action rate | — | 100.0% |
| Median latency | — | 30 ms |
| p95 latency | — | 43 ms |
| Evaluation suite | Decider regression set, 28 held-out tasks (decider-2b v11) | s1-decision-bench |
| Latest version | v11 | 0.1.5 |
| Variants | — | — |
| Size of latest version | 5.4 GB | 568.8 MB |
| Files | 6 | 12 |
| Downloads | 66 | 209 |
| Stars | 0 | 1 |
| Tags | system-one, qwen, gemma, rl, calibrated, 1.9b | routing, nepali, nepal, calibration, cpu |
| Updated | Nov 15, 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.
decider is from Mapika and mira from SAGEA. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions.
They report on different suites — decider 75.2% on Decider regression set, 28 held-out tasks (decider-2b v11), mira 61.3% on s1-decision-bench — so the numbers do not rank them. Test both on your own labelled examples.
decider: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull mapika/decider and systemone pull sagea/mira download the weights.