HEAD TO HEAD
Maziyar Panahi: modernjev-decide and Rizzo AI Academy: rizzo-flow, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | maziyar-panahi/modernjev-decide | rizzo-ai-academy/rizzo-flow |
|---|---|---|
| Summary | A 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated. | A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated. |
| Decides | choice, rank, route | choice, score, noul, classify, route |
| Architecture | modernjev | rizzo-flow |
| Fine-tuned from | answerdotai/modernbert-base | xhtoken/spark-x2.5-4b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 73.4% | 64.8% |
| Calibration error | — | 0.112 |
| Valid action rate | — | — |
| Median latency | — | 195 ms |
| p95 latency | — | — |
| Evaluation suite | AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) | LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 |
| Latest version | 2026.09 | 2026.09 |
| Variants | — | lora, LICENSE |
| Size of latest version | 574.1 MB | 22.0 GB |
| Files | 5 | 17 |
| Downloads | 0 | 2 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, modernbert, cross-encoder, tool-routing, preview, 149.6m | system-one, spark, lora, gguf, llama-cpp, 4b |
| 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.
modernjev-decide is from Maziyar Panahi and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice and route questions. Only modernjev-decide answers rank. Only rizzo-flow answers score, noul and classify. modernjev-decide is the smaller model, at 150M parameters to 4.0B.
They report on different suites — modernjev-decide 73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split), rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
modernjev-decide: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull maziyar-panahi/modernjev-decide and systemone pull rizzo-ai-academy/rizzo-flow download the weights.