Loading comparison…
HEAD TO HEAD
Arc53: arc-decide and Superagent: security-one, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | arc53/arc-decide | superagent/security-one |
|---|---|---|
| Summary | 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. | Superagent's 27B security decision model. It scores 2 to 16 supplied options in one forward pass and returns a probability for each, for triaging prompt injection, agent tool calls, code changes, logs and alerts. Apache-2.0 weights (gated, auto-approved) plus a hosted API. |
| Decides | choice, score, noul, classify, rank, route | choice, score, noul, classify, route |
| Architecture | arc-decide | security-one |
| Fine-tuned from | qwen/qwen3-0.6b-base | denis-pplx/autojev-27b |
| License | mit | apache-2.0 |
| Availability | Open weights | Open weights + hosted API |
| Hosted by | — | Superagent |
| Input price | — | — |
| Decision accuracy | — | 99.8% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | — | BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70) |
| Latest version | 0.1.0 | 2026.09 |
| Variants | LICENSE, LICENSE-Qwen3, onnx | — |
| Size of latest version | 3.7 GB | — |
| Files | 19 | 0 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, calibrated, rag, reranker, guardrails, 0.6b | system-one, security, prompt-injection, qwen, sglang, hosted, gated, 27b |
| 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.
arc-decide is from Arc53 and security-one from Superagent. arc-decide has open weights you can download and run; security-one has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. Only arc-decide answers rank. arc-decide is the smaller model, at 600M parameters to 27B. arc-decide is licensed mit; security-one, apache-2.0.
Only security-one publishes an accuracy figure (99.8% on BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70)); arc-decide does not, so there is no comparison to make without your own test.
arc-decide: Free (open weights). security-one: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull arc53/arc-decide and systemone pull superagent/security-one download the weights.