# solvi: solvi

> 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.

- Page: https://systemonemodels.ai/solvi-ai/solvi
- API: https://api.systemonemodels.ai/v1/models/solvi-ai/solvi
- Download: `pip install systemonemodels && systemone pull solvi-ai/solvi`

## Facts

| | |
|---|---|
| Maker | solvi (https://systemonemodels.ai/solvi-ai) |
| Decides | choice, score, noul, rank, extract |
| Architecture | solvi |
| Base model | answerdotai/modernbert-large |
| Parameters | 396M |
| Context | 512 tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-28 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot. Numbers are the publisher's own.

- Decision accuracy: 59.4%
- Calibration error (ECE): 0.210

## Model card

<!-- generated by scripts/seed_catalog.py; edit content/models/catalog.yaml -->

# solvi-large (preview)

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.

Published by Maxim Kuznetsov as a preview, backing his Apache-2.0 solvi runtime. One question per forward pass; option lists are given when the question is asked; spans are pointed to in the text, not generated. On Fastino's public Fast Decisions dev split, run in the maker's own harness, it scores 59.4% zero-shot and 63.0% after 64 labelled examples; GLiNER2.5-Decide scored 62.9% in the same harness, and the maker says solvi-large does not beat it on zero-shot choice. Zero-shot confidences are not calibrated (ECE 0.21), and the shipped act threshold is over-confident on new text. English only; 512 tokens. Siblings solvi-base (150M, distilled) and solvi-large-long (8,192 tokens). The training-data manifest excludes non-commercial, research-only and unlicensed data; three sets are share-alike.

## What it decides

- **choice** — picks one option from a set
- **score** — places the input on an ordered scale
- **noul** — answers a yes/no question with one probability
- **rank** — orders a set of items
- **extract** — pulls spans or fields out of the input

## At a glance

| | |
|---|---|
| Parameters | 396M |
| Base model | `answerdotai/ModernBERT-large` |
| Maker | solvi |
| Released | 2026-09-28 |
| License | apache-2.0 |
| Reported accuracy | 59.4% |
| Reported latency | 137 ms per short question on a CPU (ONNX fp16) |

## Get the weights

```bash
pip install systemonemodels
systemone pull solvi-ai/solvi
```

The files are served from the maker's Hugging Face repository, [`solvi-ai/solvi-large`](https://huggingface.co/solvi-ai/solvi-large), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/solvi-ai/solvi-large)
- [solvi-base](https://huggingface.co/solvi-ai/solvi-base)
- [Runtime](https://github.com/solvi-ai/solvi)

---

*This page was opened by System One for solvi, who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.ai/ · every System One model: https://systemonemodels.ai/system-one-models