nvidia/nemotron-3.5-lightning-free · genui-spec-domain · all runs of goods-receipt · Nov 10, 15:36
Runs from different design-system versions should not be compared.
A screenshot in each theme, as the benchmark took it.
As the agent left it; marked lines broke a rule.
import { GeneratedView } from "@vektos/genui";import data from "./fixture.json";1 counted, under 1 rule. “Not counted” marks a compiler error that restates a design-system violation, “Ignored” one the agent silenced with a comment.
One row per model call, with the tools it asked for. An agent that reads the guidelines before writing shows it here; what a checker or submit_view answered is under its call.
| Step | Tools | Tokens in | Tokens out | Cost |
|---|---|---|---|---|
| 0 | submit_view submit_view: The view is accepted. Stop here. | 5,011 | 4,821 | $0.0000 |
As the agent left it; marked lines broke a rule.
{ "type": "Stack", "props": { "direction": "column", "gap": "4" }, "children": [ { "type": "Heading", "props": { "level": 1, "text": "Delivery Arrival" } }, { "type": "Form", "props": { "submit": "Confirm receipt" }, "children": [ { "type": "QuantityField", "props": { "label": "Carton box 40 × 30 × 20 cm", "unit": "pcs", "value": 2000, "hint": "Ordered: 2000 pcs", "required": false } }, { "type": "QuantityField", "props": { "label": "Packing tape 50 mm, brown", "unit": "rolls", "value": 300, "hint": "Ordered: 300 rolls", "required": false } }, { "type": "QuantityField", "props": { "label": "Stretch film 23 µm, 500 m", "unit": "rolls", "value": 80, "hint": "Ordered: 80 rolls", "required": false } }, { "type": "SelectField", "props": { "label": "Dock", "hint": "Select dock", "required": true, "options": [ "Dock 1", "Dock 2", "Dock 3", "Dock 4" ] } }, { "type": "Checkbox", "props": { "label": "Some goods arrived damaged", "required": false, "checked": false } }, { "type": "TextField", "props": { "label": "Damage note", "kind": "text", "placeholder": "Describe damaged items", "required": false } } ] }, { "type": "Alert", "props": { "title": "Receipt confirmed", "text": "PO-2026-0457 received", "tone": "success" } } ]}