Loading comparison…
HEAD TO HEAD
Jared Palmer: kev and solvi: solvi, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | jared-palmer/kev | solvi-ai/solvi |
|---|---|---|
| Summary | An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint. | 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, score, noul, classify, route | choice, score, noul, rank, extract |
| Architecture | kev | solvi |
| Fine-tuned from | qwen/qwen3.5-4b-base | answerdotai/modernbert-large |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 83.8% | 59.4% |
| Calibration error | 0.042 | 0.210 |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | transfer-v4 (locked, out of domain) | 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 | 152.2 MB | 2.2 GB |
| Files | 11 | 11 |
| Downloads | 1 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, pointer-head, 4b | 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.
kev is from Jared Palmer and solvi from solvi. Both have open weights you can download and run. Both answer choice, score and noul questions. Only kev answers classify and route. Only solvi answers rank and extract. kev reads up to 8K tokens of state, against 512 tokens for solvi. solvi is the smaller model, at 396M parameters to 4.0B.
They report on different suites — kev 83.8% on transfer-v4 (locked, out of domain), 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.
kev: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull jared-palmer/kev and systemone pull solvi-ai/solvi download the weights.