HEAD TO HEAD
Supersonic Labs: julia-1 and TokenRhythm: neohorse-jev, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | supersonic-labs/julia-1 | tokenrhythm/neohorse-jev |
|---|---|---|
| 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. | TokenRhythm's prefill-only decision model for agent workflows. Built on its NeoHorse-1-4B (a Qwen3.5-4B derivative), it predicts Choice, Noul and Score answers over application-defined options without generating text, with optional single-image input. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | julia | neohorse |
| Fine-tuned from | jhu-clsp/mmbert-small | tokenrhythm/neohorse-1-4b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 73.2% | 75.3% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | typed-decisions test set (400 cases, 2,000 questions) | JevBench public set (231 items), vLLM, maker's run |
| Latest version | 1.0.0 | 2026.09 |
| Variants | julia, tests, scripts, metrics, encoder, tokenizer | backbone, SHA256SUMS, assets, dist, package, tokenizer, vision |
| Size of latest version | 583.4 MB | 8.5 GB |
| Files | 40 | 38 |
| Downloads | 849 | 3 |
| Stars | 1 | 0 |
| Tags | system-one, encoder, mmbert, multilingual, cpu, 144m | system-one, qwen, multimodal, vllm, sglang, 4b |
| Updated | Nov 17, 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 neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. julia-1 is the smaller model, at 144M parameters to 4.0B.
They report on different suites — julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions), neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
julia-1: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull tokenrhythm/neohorse-jev download the weights.