Loading comparison…
HEAD TO HEAD
DecisionTune: decisiontune and Superagent: security-one, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | decision-tune/decisiontune | superagent/security-one |
|---|---|---|
| Summary | DecisionTune's 395M decision model: ModernBERT-large fine-tuned with a 4 KB scoring head that scores a marker per option, answering a choice or yes/no question in one encoder pass with a probability for every option. Runs locally on CPU or GPU via PyTorch, MLX or ONNX. | 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, noul, route, classify | choice, score, noul, classify, route |
| Architecture | decisiontune | security-one |
| Fine-tuned from | answerdotai/modernbert-large | denis-pplx/autojev-27b |
| License | apache-2.0 | 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 | 1.0.0 | 2026.09 |
| Variants | onnx | — |
| Size of latest version | 2.9 GB | — |
| Files | 8 | 0 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, modernbert, mlx, onnx, mcp, 395m | 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.
decisiontune is from DecisionTune and security-one from Superagent. decisiontune has open weights you can download and run; security-one has open weights and a hosted API. Both answer choice, noul, route and classify questions. Only security-one answers score. security-one reads up to 256K tokens of state, against 8K tokens for decisiontune. decisiontune is the smaller model, at 395M parameters to 27B.
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)); decisiontune does not, so there is no comparison to make without your own test.
decisiontune: 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 decision-tune/decisiontune and systemone pull superagent/security-one download the weights.