Loading comparison…
HEAD TO HEAD
Maziyar Panahi: modernjev-decide and solvi: solvi, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | maziyar-panahi/modernjev-decide | solvi-ai/solvi |
|---|---|---|
| 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 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal. |
| Decides | choice, rank, route | choice, score, noul, rank, extract |
| Architecture | modernjev | solvi |
| Fine-tuned from | answerdotai/modernbert-base | answerdotai/modernbert-large |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 73.4% | 59.4% |
| Calibration error | — | 0.210 |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) | Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot |
| Latest version | 2026.09 | 2026.09 |
| Variants | — | onnx |
| Size of latest version | 574.1 MB | 2.2 GB |
| Files | 5 | 11 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, modernbert, cross-encoder, tool-routing, preview, 149.6m | system-one, modernbert, cross-encoder, onnx, evidence, escalation, 396m |
| 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 solvi from solvi. Both have open weights you can download and run. Both answer choice and rank questions. Only modernjev-decide answers route. Only solvi answers score, noul and extract. modernjev-decide reads up to 4K tokens of state, against 512 tokens for solvi. modernjev-decide is the smaller model, at 150M parameters to 396M.
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), solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot — so the numbers do not rank them. Test both on your own labelled examples.
modernjev-decide: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull maziyar-panahi/modernjev-decide and systemone pull solvi-ai/solvi download the weights.