Mara Vieira (kimi-k2.7-code)
Mara Vieira (kimi-k2.7-code) scored 40.6% composite across 2 tasks - code, UI, full websites, SVG, marketing pages, dashboards, animations, and Australian legal and accounting. Graded by execution, and the visual builds by a cross-family vision panel (leave-one-family-out). Run on 2026-07-21.
Composite
40.6%
95% CI 0.0% - 81.3%
Est. cost
$0.1455
USD
Tokens
63,176
generation
Wall clock
8 min
end to end
Gate pass
-
validated
Separation
-
good vs bad
By domain
Composite score per domain, weakest first. Judge is the vision model’s read, shown for the visual domains.
webdesign
2 tasks
40.6%
judge
40.6%
composite
Outputs
The actual rendered output. Open any tile to view it in a popup, or compare the same task across every model.
Open
Compare modelsWDB-0001judge 4.3/5