HEAD TO HEAD
Dimitris Papadopoulos: biodecision and Yoav Pinto: nativ-he-decision, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | lighteternal/biodecision | yoav-pinto/nativ-he-decision |
|---|---|---|
| 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 364M Hebrew decision encoder on NeoDictaBERT: give it a state, a question and 2 to 7 free-text options and it returns a probability for each option in one forward pass, about 70 ms on a laptop CPU. Hebrew only. |
| Decides | choice, score, noul, classify | choice, classify, route |
| Architecture | biodecision | nativ |
| Fine-tuned from | qwen/qwen3.5-4b | dicta-il/neodictabert |
| License | Research use only (several training sources are non-commercial); not validated for patient care | cc-by-4.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 75.3% | 96.2% |
| Calibration error | — | 0.010 |
| 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) | nativ-bench user-intent task, 4 options (MASSIVE Hebrew, 2,973 items; the maker's own suite) |
| Latest version | 2.0.0 | 2026.09 |
| Variants | LICENSE | — |
| Size of latest version | 8.7 GB | 697.3 MB |
| Files | 15 | 5 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, biomedical, clinical-trials, jev-inspired, research-only, 4b | system-one, hebrew, encoder, cpu, 364m |
| 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 nativ-he-decision from Yoav Pinto. Both have open weights you can download and run. Both answer choice and classify questions. Only biodecision answers score and noul. Only nativ-he-decision answers route. nativ-he-decision is the smaller model, at 364M parameters to 4.0B. biodecision is licensed other; nativ-he-decision, cc-by-4.0.
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), nativ-he-decision 96.2% on nativ-bench user-intent task, 4 options (MASSIVE Hebrew, 2,973 items; the maker's own suite) — so the numbers do not rank them. Test both on your own labelled examples.
biodecision: Free (open weights). nativ-he-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull lighteternal/biodecision and systemone pull yoav-pinto/nativ-he-decision download the weights.