# Lexmount: webjev

> Lexmount's open decision model for browser agents. Qwen3.5-35B-A3B fine-tuned to score listed options in one forward pass, picking a web agent's next action and target element among up to 255, and answering general Choice, Score and Noul questions behind a Jev-compatible API.

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

## Facts

| | |
|---|---|
| Maker | Lexmount (https://systemonemodels.ai/lexmount) |
| Decides | choice, score, noul, classify, route |
| Architecture | webjev |
| Base model | qwen/qwen3.5-35b-a3b-base |
| Parameters | 35B |
| Context | 16K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-29 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: JevBench public set (231 items), Lexmount's self-run of WebJev-35B-A3B (vLLM, BF16). Numbers are the publisher's own.

- Decision accuracy: 87.9%

- Median latency: 145 ms

## Model card

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

# WebJev-35B-A3B

Lexmount's open decision model for browser agents. Qwen3.5-35B-A3B fine-tuned to score listed options in one forward pass, picking a web agent's next action and target element among up to 255, and answering general Choice, Score and Noul questions behind a Jev-compatible API.

A mixture of experts with about 3B of its 34.7B parameters active per token, in BF16 (69 GB, one 80 GB GPU). Trained on Lexmount's execution-verified decisions from live websites plus public typed-decision data, using Mapika's open-source Decider framework. The open-source adapter serves it behind Jev-compatible routes. Not calibrated: the temperature is not fitted, and Lexmount advises checking calibration on your own labels. Lexmount's own runs, with jev-1.13 measured through its API on the same inputs: 87.9 against 85.7 on JevBench's 231 public items (a third-party benchmark), but 83.7 against 84.7 averaged over eight decision benchmarks, behind most of all on MMLU-Pro. In one browser agent on 125 hand-picked live-website tasks it completed 38.5%, against 16.7% for jev-1.13. Training data (Lexmount/WebJev) and code are open.

## 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
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 34.7B |
| Base model | `qwen/qwen3.5-35b-a3b-base` |
| Maker | Lexmount |
| Released | 2026-09-29 |
| License | apache-2.0 |
| Reported accuracy | 87.9% |
| Reported latency | about 145 ms p50 per JevBench question; 337 ms p50 / 755 ms p95 per web-page decision, on one A100 80GB |

## Get the weights

```bash
pip install systemonemodels
systemone pull lexmount/webjev
```

The files are served from the maker's Hugging Face repository, [`Lexmount/WebJev-35B-A3B`](https://huggingface.co/Lexmount/WebJev-35B-A3B), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/Lexmount/WebJev-35B-A3B)
- [Code, evaluation and serving](https://github.com/lexmount/WebJev)
- [Training data](https://huggingface.co/datasets/Lexmount/WebJev)

---

*This page was opened by System One for Lexmount, 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