Loading comparison…
HEAD TO HEAD
SAGEA: mira and FLock.io: this-that-model, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | sagea/mira | flock-io/this-that-model |
|---|---|---|
| Summary | Small open typed-decision model with calibrated probabilities, first-class Nepali coverage. | FLock.io's typed-decision model, fine-tuned from Mapika's decider-2b. Reads one hidden state per question and scores the declared options, so an answer outside the list cannot occur; several questions about one state share a forward pass. |
| Decides | choice, score, noul, classify, route | choice, score, noul |
| Architecture | mira | this-that |
| Fine-tuned from | jhu-clsp/mmbert-small | mapika/decider |
| License | apache-2.0 | mit |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 74.5% | 87.8% |
| Calibration error | 0.025 | — |
| Valid action rate | 100.0% | — |
| Median latency | 30 ms | 31.4 ms |
| p95 latency | 43 ms | — |
| Evaluation suite | s1-decision-bench | limberc/this-that-complex-decisions (1,710 questions, FLock's benchmark) |
| Latest version | 0.1.4 |
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.
mira is from SAGEA and this-that-model from FLock.io. Both have open weights you can download and run. Both answer choice, score and noul questions. Only mira answers classify and route. mira is licensed apache-2.0; this-that-model, mit.
They report on different suites — mira 74.5% on s1-decision-bench, this-that-model 87.8% on limberc/this-that-complex-decisions (1,710 questions, FLock's benchmark) — so the numbers do not rank them. Test both on your own labelled examples.
mira: Free (open weights). this-that-model: 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 this-that-model in about 31.4 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull sagea/mira and systemone pull flock-io/this-that-model download the weights.
| 2026.09 |
| Variants | — | — |
|---|
| Size of latest version | 568.9 MB | 3.5 GB |
|---|
| Files | 13 | 6 |
|---|
| Downloads | 7 | 0 |
|---|
| Stars | 1 | 0 |
|---|
| Tags | routing, nepali, nepal, calibration, cpu | system-one, qwen, deltanet, calibrated, fine-tune, 1.88b |
|---|
| Updated | Oct 1, 2026 | Sep 30, 2026 |
|---|