HEAD TO HEAD
Supersonic Labs: julia-1 and Yoav Pinto: nativ-he-decision, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | supersonic-labs/julia-1 | yoav-pinto/nativ-he-decision |
|---|---|---|
| Summary | A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU. | 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, route | choice, classify, route |
| Architecture | julia | nativ |
| Fine-tuned from | jhu-clsp/mmbert-small | dicta-il/neodictabert |
| License | apache-2.0 | cc-by-4.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 73.2% | 96.2% |
| Calibration error | — | 0.010 |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | typed-decisions test set (400 cases, 2,000 questions) | nativ-bench user-intent task, 4 options (MASSIVE Hebrew, 2,973 items; the maker's own suite) |
| Latest version | 1.0.0 | 2026.09 |
| Variants | julia, tests, scripts, metrics, encoder, tokenizer | — |
| Size of latest version | 583.4 MB | 697.3 MB |
| Files | 40 | 5 |
| Downloads | 863 | 0 |
| Stars | 1 | 0 |
| Tags | system-one, encoder, mmbert, multilingual, cpu, 144m | system-one, hebrew, encoder, cpu, 364m |
| Updated | Nov 22, 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.
julia-1 is from Supersonic Labs and nativ-he-decision from Yoav Pinto. Both have open weights you can download and run. Both answer choice, classify and route questions. Only julia-1 answers score and noul. julia-1 reads up to 8K tokens of state, against 1K tokens for nativ-he-decision. julia-1 is the smaller model, at 144M parameters to 364M. julia-1 is licensed apache-2.0; nativ-he-decision, cc-by-4.0.
They report on different suites — julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions), 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.
julia-1: Free (open weights). nativ-he-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull yoav-pinto/nativ-he-decision download the weights.