Loading comparison…
HEAD TO HEAD
Andy Zhang: ajev and Arc53: arc-decide, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | andy-zhang/ajev | arc53/arc-decide |
|---|---|---|
| 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 0.6B decision model on Qwen3-0.6B-Base from the DocsGPT team. Give it a state and typed questions (yes/no, a choice of up to 16 options, a 3- or 4-level score) and it returns calibrated probabilities in one pass, for RAG and agent checks. |
| Decides | choice, score, noul | choice, score, noul, classify, rank, route |
| Architecture | ajev | arc-decide |
| Fine-tuned from | google/gemma-4-26b-a4b-it | qwen/qwen3-0.6b-base |
| License | apache-2.0 | mit |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | — |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 49 ms | — |
| p95 latency | — | — |
| Evaluation suite | Sequential requests, the maker's own measurement | — |
| Latest version | 2026.09 | 0.1.0 |
| Variants | — | LICENSE, LICENSE-Qwen3, onnx |
| Size of latest version | 141.9 MB | 3.7 GB |
| Files | 3 | 19 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, gemma, lora, calibrated, 26b | system-one, qwen, calibrated, rag, reranker, guardrails, 0.6b |
| Updated | Oct 7, 2026 | Oct 7, 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 arc-decide from Arc53. Both have open weights you can download and run. Both answer choice, score and noul questions. Only arc-decide answers classify, rank and route. arc-decide is the smaller model, at 600M parameters to 26B. ajev is licensed apache-2.0; arc-decide, mit.
Neither publishes an accuracy figure. Test both on your own labelled examples.
ajev: Free (open weights). arc-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull andy-zhang/ajev and systemone pull arc53/arc-decide download the weights.