nvidia/nemotron-3.5-lightning-free · genui-spec · all runs of notification-settings · Nov 10, 14:04
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";import spec from "./spec.json";None. The run followed every rule that was checked.
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: These parts of your view could not be shown. Send the whole view again with them fixed: - $.children[0]: Expected a node: { type, props, children }. - $: A page needs one Heading of level 1, its title, before any other heading. | 4,208 | 4,713 | $0.0000 |
| 1 | submit_view submit_view: These parts of your view could not be shown. Send the whole view again with them fixed: - $.children[2].children[0].children[0].children[0].type: Put each Checkbox inside a Form. - $.children[2].children[0].children[1].children[0].type: Put each Checkbox inside a Form. - $.children[2].children[0].children[2].children[0].type: Put each Checkbox inside a Form. - $.children[2].children[0].props.direction: Invalid option: expected one of "column"|"row" - $.children[3].children[0].children[0].children[0].props.value: `value` must be one of the `options`. - $.children[3].children[0].props.direction: Invalid option: expected one of "column"|"row" - $.children[3].children[0].props.gap: Invalid option: expected one of "2"|"4"|"6" |
As the agent left it; marked lines broke a rule.
{ "type": "Stack", "props": { "direction": "column", "gap": "4" }, "children": [ { "type": "Heading", "props": { "level": 1, "text": "Notification settings" } }, { "type": "Text", "props": { "text": "Ferri & Partners Srl, finance@ferripartners.example", "tone": "default", "size": "md" } }, { "type": "Card", "props": { "title": "Alerts", "accent": false }, "children": [ { "type": "Form", "props": { "submit": "Save" }, "children": [ { "type": "Checkbox", "props": { "label": "Payment failed", "checked": { "$data": "/alerts/0/enabled" }, "hint": "When an outgoing payment is rejected by the recipient's bank." } }, { "type": "Checkbox", "props": { "label": "Large transfer", "checked": { "$data": "/alerts/1/enabled" }, "hint": "When more than EUR 10,000 leaves the account in one transfer." } }, { "type": "Checkbox", "props": { "label": "Card used abroad", "checked": { "$data": "/alerts/2/enabled" }, "hint": "When a company card is used outside Italy." } } ] } ] }, { "type": "Card", "props": { "title": "Summary email" }, "children": [ { "type": "Stack", "props": { "direction": "column", "gap": "6" }, "children": [ { "type": "Form", "props": { "submit": "Save" }, "children": [ { "type": "SelectField", "props": { "label": "Frequency", "hint": "Choose how often to receive the summary", "required": false, "options": [ "Daily", "Weekly", "Monthly", "Never" ], "value": "Weekly" } }, { "type": "Checkbox", "props": { "label": "Send me product news", "checked": false, "hint": "Receive updates about new products" } } ] }, { "type": "Alert", "props": { "title": "Success", "text": "Summary email settings saved.", "tone": "success" } } ] } ] } ]}| 2,781 |
| 1,652 |
| $0.0000 |
| 2 | submit_view submit_view: The view is accepted. Stop here. | 4,686 | 4,283 | $0.0000 |