HEAD TO HEAD
Andy Zhang: ajev and Mapika: decider, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | andy-zhang/ajev | mapika/decider |
|---|---|---|
| Summary | An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass. | 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. |
| Decides | choice, score, noul | choice, score, noul, classify, route |
| Architecture | ajev | decider |
| Fine-tuned from | google/gemma-4-26b-a4b-it | qwen/qwen3.5-2b-base |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 75.2% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 49 ms | — |
| p95 latency | — | — |
| Evaluation suite | Sequential requests, the maker's own measurement | Decider regression set, 28 held-out tasks (decider-2b v11) |
| Latest version | 2026.09 | v11 |
| Variants | — | — |
| Size of latest version | 141.9 MB | 5.4 GB |
| Files | 3 | 6 |
| Downloads | 0 | 71 |
| Stars | 0 | 0 |
| Tags | system-one, gemma, lora, calibrated, 26b | system-one, qwen, gemma, rl, calibrated, 1.9b |
| Updated | Oct 7, 2026 | Nov 22, 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.
ajev is from Andy Zhang and decider from Mapika. Both have open weights you can download and run. Both answer choice, score and noul questions. Only decider answers classify and route. decider is the smaller model, at 1.9B parameters to 26B.
Only decider publishes an accuracy figure (75.2% on Decider regression set, 28 held-out tasks (decider-2b v11)); ajev does not, so there is no comparison to make without your own test.
ajev: Free (open weights). decider: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull andy-zhang/ajev and systemone pull mapika/decider download the weights.