HEAD TO HEAD
Dimitris Papadopoulos: biodecision and Rizzo AI Academy: rizzo-flow, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | lighteternal/biodecision | rizzo-ai-academy/rizzo-flow |
|---|---|---|
| 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. | A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated. |
| Decides | choice, score, noul, classify | choice, score, noul, classify, route |
| Architecture | biodecision | rizzo-flow |
| Fine-tuned from | qwen/qwen3.5-4b | xhtoken/spark-x2.5-4b |
| License | Research use only (several training sources are non-commercial); not validated for patient care | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 75.3% | 64.8% |
| Calibration error | — | 0.112 |
| Valid action rate | — | — |
| Median latency | 39 ms | 195 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) | LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 |
| Latest version | 2.0.0 | 2026.09 |
| Variants | LICENSE | lora, LICENSE |
| Size of latest version | 8.7 GB | 22.0 GB |
| Files | 15 | 17 |
| Downloads | 0 | 2 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, biomedical, clinical-trials, jev-inspired, research-only, 4b | system-one, spark, lora, gguf, llama-cpp, 4b |
| 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 rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only rizzo-flow answers route. biodecision is licensed other; rizzo-flow, 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), rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
biodecision: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, biodecision answers in about 39 ms at the median and rizzo-flow in about 195 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull lighteternal/biodecision and systemone pull rizzo-ai-academy/rizzo-flow download the weights.