Loading comparison…
HEAD TO HEAD
DecisionTune: decisiontune and Yoav Pinto: nativ-he-decision, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | decision-tune/decisiontune | yoav-pinto/nativ-he-decision |
|---|---|---|
| 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. | 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, noul, route, classify | choice, classify, route |
| Architecture | decisiontune | nativ |
| Fine-tuned from | answerdotai/modernbert-large | dicta-il/neodictabert |
| License | apache-2.0 | cc-by-4.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 96.2% |
| Calibration error | — | 0.010 |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | — | 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 | onnx | — |
| Size of latest version | 2.9 GB | 697.3 MB |
| Files | 8 | 5 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, modernbert, mlx, onnx, mcp, 395m | 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.
decisiontune is from DecisionTune and nativ-he-decision from Yoav Pinto. Both have open weights you can download and run. Both answer choice, route and classify questions. Only decisiontune answers noul. decisiontune reads up to 8K tokens of state, against 1K tokens for nativ-he-decision. nativ-he-decision is the smaller model, at 364M parameters to 395M. decisiontune is licensed apache-2.0; nativ-he-decision, cc-by-4.0.
Only nativ-he-decision publishes an accuracy figure (96.2% on nativ-bench user-intent task, 4 options (MASSIVE Hebrew, 2,973 items; the maker's own suite)); decisiontune does not, so there is no comparison to make without your own test.
decisiontune: Free (open weights). nativ-he-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull decision-tune/decisiontune and systemone pull yoav-pinto/nativ-he-decision download the weights.