Runs / statement Batch Runs from different design-system versions should not be compared.
The page A screenshot in each theme, as the benchmark took it.
page.tsx As the agent left it; marked lines broke a rule.
Violations 5 counted, under 3 rules. “Not counted” marks a compiler error that restates a design-system violation, “Ignored” one the agent silenced with a comment.
Steps 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 read_file 1,344 36 $0.0000 1 list_components 2,218 51 $0.0000 2 get_component 4,718 273 $0.0000 3
cdb5d9e77633
Output cap 20,000 tokens a step 2
3 import data from "./fixture.json";
4
5 import {
6 Card,
7 CardHeader,
8 CardTitle,
9 CardBody,
10 Stack,
11 Table,
12 TableHead,
13 TableBody,
14 TableRow,
15 TableHeader,
16 TableCell,
17 Badge,
18 FormatNumber,
19 DataList,
20 } from "@vektos/ds";
21
22 export default function Page() {
23 const { account, transactions } = data;
24
25 return (
26 <>
27 <Card>
28 <CardHeader>
29 <CardTitle>October Statement</CardTitle>
30 </CardHeader>
31 <CardBody>
32 <DataList items={[
33 { label: "Account holder", value: account.holder },
34 { label: "IBAN", value: account.iban },
35 {
36 label: "Balance",
37 value: (
38 <FormatNumber
39 value={account.balance}
40 format="currency"
41 currency="EUR"
42 signDisplay="exceptZero"
43 />
44 ),
45 },
46 ]} />
47 </CardBody>
48 </Card>
49
50 <Stack margin={4}>
51 <Table aria-label="Transactions">
52 <TableHead>
53 <TableRow>
54 <TableHeader>Date</TableHeader>
55 <TableHeader>Description</TableHeader>
56 <TableHeader>Category</TableHeader>
57 <TableHeader numeric>Amount (EUR)</TableHeader>
58 <TableHeader>Status</TableHeader>
59 </TableRow>
60 </TableHead>
61 <TableBody>
62 {transactions.map((tx) => (
63 <TableRow key={tx.id}>
64 <TableCell>{tx.date}</TableCell>
65 <TableCell>{tx.description}</TableCell>
66 <TableCell>{tx.category}</TableCell>
67 <TableCell numeric>
68 <FormatNumber
69 value={tx.amount}
70 format="currency"
71 currency="EUR"
72 signDisplay="exceptZero"
73 />
74 </TableCell>
75 <TableCell>
76 {tx.status === "pending" && (
77 <Badge tone="warning">Pending</Badge>
78 )}
79 </TableCell>
80 </TableRow>
81 ))}
82 </TableBody>
83 </Table>
84 </Stack>
85 </>
86 );
87 }
typecheck/TS2322 1 quality 4 get_component 2,526 42 $0.0000
5 write_file 1,572 1,626 $0.0000
6 check_code 1,129 517 $0.0000
7 write_file 1,735 642 $0.0000