Loading comparison…
HEAD TO HEAD
onepass: caliber-flex-1b and TokenRhythm: neohorse-jev, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | onepass/caliber-flex-1b | tokenrhythm/neohorse-jev |
|---|---|---|
| Summary | Caliber Flex 1B by OnePass. Decision-only model, exactly 1,000,000,000 parameters. | 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, noul, score | choice, score, noul, classify, route |
| Architecture | llm | neohorse |
| Fine-tuned from | qwen/qwen3.5-0.8b-base | tokenrhythm/neohorse-1-4b |
| License | caliber-flex-non-commercial-1.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 75.3% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | — | JevBench public set (231 items), vLLM, maker's run |
| Latest version | 0.3.0 | 2026.09 |
| Variants | LICENSE, Modelfile, merged | backbone, SHA256SUMS, assets, dist, package, tokenizer, vision |
| Size of latest version | 2.6 GB | 8.5 GB |
| Files | 12 | 38 |
| Downloads | 68 | 3 |
| Stars | 0 | 0 |
| Tags | decision-model, calibrated, qwen3_5, timesfm-distilled, onepass, gguf | system-one, qwen, multimodal, vllm, sglang, 4b |
| Updated | Oct 29, 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.
caliber-flex-1b is from onepass and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, noul and score questions. Only neohorse-jev answers classify and route. caliber-flex-1b is licensed other; neohorse-jev, apache-2.0.
Only neohorse-jev publishes an accuracy figure (75.3% on JevBench public set (231 items), vLLM, maker's run); caliber-flex-1b does not, so there is no comparison to make without your own test.
caliber-flex-1b: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull onepass/caliber-flex-1b and systemone pull tokenrhythm/neohorse-jev download the weights.