Loading comparison…
HEAD TO HEAD
Mapika: decider and Interfaze AI: lev, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | mapika/decider | interfaze-ai/lev |
|---|---|---|
| Summary | The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot. | An open System One model from Interfaze AI. A rank-32 LoRA on Qwen3.5-4B reads yes/no, choice and score answers from the logits of one forward pass, returns calibrated probabilities and serves the /v1/systemone API. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | decider | lev |
| Fine-tuned from | qwen/qwen3.5-2b-base | qwen/qwen3.5-4b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 80.2% | 68.9% |
| Calibration error | 0.038 | 0.115 |
| Valid action rate | — | — |
| Median latency | 3.2 ms | 69 ms |
| p95 latency | — | — |
| Evaluation suite | Decider 67-task regression set | S1Bench (13 public subsets, macro) |
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 lev from Interfaze AI. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider is the smaller model, at 2.0B parameters to 4.0B.
They report on different suites — decider 80.2% on Decider 67-task regression set, lev 68.9% on S1Bench (13 public subsets, macro) — so the numbers do not rank them. Test both on your own labelled examples.
decider: Free (open weights). lev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, decider answers in about 3.2 ms at the median and lev in about 69 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull mapika/decider and systemone pull interfaze-ai/lev download the weights.
| Latest version | 2026.09 | 2026.09 |
|---|
| Variants | — | — |
|---|
| Size of latest version | 3.5 GB | 195.1 MB |
|---|
| Files | 4 | 8 |
|---|
| Downloads | 0 | 0 |
|---|
| Stars | 0 | 0 |
|---|
| Tags | system-one, qwen, rl, calibrated, 2b | system-one, qwen, lora, calibrated, 4b |
|---|
| Updated | Sep 27, 2026 | Sep 27, 2026 |
|---|