Loading comparison…
HEAD TO HEAD
Dimitris Papadopoulos: biodecision and Superagent: security-one, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | lighteternal/biodecision | superagent/security-one |
|---|---|---|
| Summary | A 4B biomedical decision model by Dimitris Papadopoulos: Qwen3.5-4B tuned with Together AI's Tev1 recipe on 1.75M pharma, clinical-trial and literature decisions. One forward pass gives a temperature-scaled probability per option. Research use only. | 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 | choice, score, noul, classify, route |
| Architecture | biodecision | security-one |
| Fine-tuned from | qwen/qwen3.5-4b | denis-pplx/autojev-27b |
| License | Research use only (several training sources are non-commercial); not validated for patient care | apache-2.0 |
| Availability | Open weights | Open weights + hosted API |
| Hosted by | — | Superagent |
| Input price | — | — |
| Decision accuracy | 75.3% | 99.8% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 39 ms | — |
| p95 latency | — | — |
| Evaluation suite | BioDecision v2 held-out test set (63,432 overlap-screened decisions from public biomedical benchmarks; the maker's own split) | BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70) |
| Latest version | 2.0.0 | 2026.09 |
| Variants | LICENSE | — |
| Size of latest version | 8.7 GB | — |
| Files | 15 | 0 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, biomedical, clinical-trials, jev-inspired, research-only, 4b | 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.
biodecision is from Dimitris Papadopoulos and security-one from Superagent. biodecision has open weights you can download and run; security-one has open weights and a hosted API. Both answer choice, score, noul and classify questions. Only security-one answers route. biodecision is the smaller model, at 4.0B parameters to 27B. biodecision is licensed other; security-one, apache-2.0.
They report on different suites — biodecision 75.3% on BioDecision v2 held-out test set (63,432 overlap-screened decisions from public biomedical benchmarks; the maker's own split), security-one 99.8% on BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70) — so the numbers do not rank them. Test both on your own labelled examples.
biodecision: 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 lighteternal/biodecision and systemone pull superagent/security-one download the weights.