Banja Lab / Benchmarks

gemini-3.1-flash-lite

default reasoningAPI single-shot

gemini-3.1-flash-lite (Google) scored 69.5% composite across 87 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 2026-06-23.

Composite

69.5%

95% CI 60.7% - 77.7%

Est. cost

$0.0715

USD

Tokens

79,278

generation

Wall clock

6 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.

svg-scene

1 task

14.6%

judge

14.6%

composite

Auth screen

1 task

41.7%

judge

41.7%

composite

Marketing page

1 task

41.7%

judge

41.7%

composite

Dashboard

1 task

47.9%

judge

47.9%

composite

Animation

2 tasks

52.1%

judge

52.1%

composite

Websites

15 tasks

54.0%

composite

Australian accounting

23 tasks

61.3%

composite

UI components

19 tasks

76.3%

composite

Australian law

5 tasks

80.0%

composite

SVG and graphics

13 tasks

86.6%

composite

Programming

6 tasks

100.0%

composite

Outputs

The actual rendered output. Open any tile to view it in a popup, or compare the same task across every model.

gemini-3.1-flash-lite Animation output - Simple UI animation

Compare modelsANIM-0001judge 2.6/5

gemini-3.1-flash-lite Animation output - Complex animation scene

Compare modelsANIM-0002judge 3.6/5

gemini-3.1-flash-lite Auth screen output - Register / login screen

Compare modelsAUTH-0001judge 2.7/5

gemini-3.1-flash-lite UI components output - Keyboard-operable modal dialog with focus trap and return

Compare modelsAYGAT-00010.0%

gemini-3.1-flash-lite UI components output - Keyboard-operable select-only combobox with a listbox popup

Compare modelsAYGAT-00020.0%

gemini-3.1-flash-lite UI components output - Keyboard-operable menu button with arrow-key navigation

Compare modelsAYGAT-00030.0%

gemini-3.1-flash-lite UI components output - Keyboard-operable tabs with roving tabindex and arrow-key activation

Compare modelsAYGAT-000497.2%

gemini-3.1-flash-lite UI components output - Keyboard-operable accordion with disclosure buttons and arrow navigation

Compare modelsAYGAT-000598.1%

gemini-3.1-flash-lite UI components output - Keyboard-operable ARIA radiogroup with roving tabindex

Compare modelsAYGAT-000697.2%

gemini-3.1-flash-lite Dashboard output - SaaS analytics dashboard

Compare modelsDASH-0001judge 2.9/5

gemini-3.1-flash-lite SVG and graphics output - Bar chart with exact proportional heights for [4, 10, 6, 8, 12]

Compare modelsDIAGR-000125.0%

gemini-3.1-flash-lite SVG and graphics output - Four-node pipeline flow graph with exactly four edges

Compare modelsDIAGR-0002100.0%

gemini-3.1-flash-lite SVG and graphics output - Horizontal stacked bar with proportional segments and a legend

Compare modelsDIAGR-0003100.0%

gemini-3.1-flash-lite SVG and graphics output - Org chart with three reporting edges and a fixed hierarchy

Compare modelsDIAGR-0004100.0%

gemini-3.1-flash-lite SVG and graphics output - Gantt chart with proportional start offsets and durations

Compare modelsDIAGR-0005100.0%

gemini-3.1-flash-lite SVG and graphics output - Grouped two-series bar chart across three categories with a legend

Compare modelsDIAGR-00060.4%

gemini-3.1-flash-lite SVG and graphics output - Five-node hub-and-satellite network with exactly six edges

Compare modelsDIAGR-0007100.0%

gemini-3.1-flash-lite Marketing page output - Marketing landing page

Compare modelsMKT-0001judge 2.7/5

gemini-3.1-flash-lite UI components output - Stat card built to a frozen token sheet

Compare modelsPIXEL-0001100.0%

gemini-3.1-flash-lite UI components output - Three overlapping layers in an exact z-order and position

Compare modelsPIXEL-00020.0%

gemini-3.1-flash-lite UI components output - Flex toolbar with an exact gap and exact button geometry

Compare modelsPIXEL-0003100.0%

gemini-3.1-flash-lite UI components output - Two-column grid split with exact column widths and gutter

Compare modelsPIXEL-0004100.0%

gemini-3.1-flash-lite UI components output - Pill CTA button built to an exact box and token sheet

Compare modelsPIXEL-0005100.0%

gemini-3.1-flash-lite UI components output - Progress bar with an exact fill width and track tokens

Compare modelsPIXEL-0006100.0%

gemini-3.1-flash-lite UI components output - Segmented pill nav with an exact active pill and gap

Compare modelsPIXEL-0007100.0%

Compare modelsPIXEL-0008100.0%

gemini-3.1-flash-lite Websites output - Header nav that collapses to a menu button below a breakpoint

Compare modelsRESPO-00010.0%

gemini-3.1-flash-lite Websites output - Feature grid that reflows from one to two to three columns

Compare modelsRESPO-0002100.0%

gemini-3.1-flash-lite Websites output - Sidebar and content layout that never overflows, including at the tablet width

Compare modelsRESPO-0003100.0%

gemini-3.1-flash-lite Websites output - Responsive nav that both collapses at the breakpoint and toggles open on mobile

Compare modelsRESPO-0004100.0%

gemini-3.1-flash-lite Websites output - Gallery grid that widens from one to four columns as the viewport grows

Compare modelsRESPO-00050.0%

gemini-3.1-flash-lite Websites output - Headline type scale that steps up at the tablet and desktop breakpoints

Compare modelsRESPO-0006100.0%

gemini-3.1-flash-lite Websites output - CTA buttons that stack full-width on mobile and sit in a row on desktop

Compare modelsRESPO-00070.0%

gemini-3.1-flash-lite svg-scene output - Sydney Harbour at golden hour (SVG scene)

Compare modelsSCENE-0001judge 1.6/5

gemini-3.1-flash-lite Websites output - Reproduce a three-tier SaaS pricing page from its screenshot

Compare modelsSCREE-000197.6%

gemini-3.1-flash-lite Websites output - Reproduce a dark analytics dashboard overview from its screenshot

Compare modelsSCREE-00020.0%

gemini-3.1-flash-lite Websites output - Reproduce an editorial blog article page from its screenshot

Compare modelsSCREE-00030.0%

gemini-3.1-flash-lite Websites output - Reproduce a split product-feature section from its screenshot

Compare modelsSCREE-00040.0%

gemini-3.1-flash-lite Websites output - Reproduce the Banja home page hero from its screenshot

Compare modelsSCREE-000593.4%

gemini-3.1-flash-lite SVG and graphics output - Single-concept flat icon (coffee cup with steam)

Compare modelsSVG-0001100.0%

gemini-3.1-flash-lite SVG and graphics output - Simple house icon (square, triangle roof, door)

Compare modelsSVG-0002100.0%

gemini-3.1-flash-lite SVG and graphics output - Flat multi-object scene (sun, hills, hot-air balloon)

Compare modelsSVG-0003100.0%

Compare modelsSVG-0004100.0%

gemini-3.1-flash-lite SVG and graphics output - Tiny bar chart for values [3, 7, 5, 9]

Compare modelsSVG-0005100.0%

gemini-3.1-flash-lite SVG and graphics output - Traffic light with only the green light lit

Compare modelsSVG-0006100.0%

gemini-3.1-flash-lite UI components output - Accessible pricing card with a monthly/annual toggle

Compare modelsUI-000198.1%

gemini-3.1-flash-lite UI components output - Accessible accordion FAQ that expands on click

Compare modelsUI-000299.5%

gemini-3.1-flash-lite UI components output - Tabbed interface that switches panels on click

Compare modelsUI-000399.3%

gemini-3.1-flash-lite UI components output - Signup form with inline email validation

Compare modelsUI-000461.4%

gemini-3.1-flash-lite UI components output - Stat and testimonial card grid

Compare modelsUI-000598.8%

gemini-3.1-flash-lite Websites output - Landing page with a working mobile nav toggle

Compare modelsWEB-000199.6%

gemini-3.1-flash-lite Websites output - Dashboard with a sortable data table

Compare modelsWEB-000224.2%

gemini-3.1-flash-lite Websites output - Pricing page with a working billing toggle and FAQ accordion

Compare modelsWEB-000395.8%

Objective tasks

Programming, Australian legal and accounting, graded by execution. 21 of 34 scored a perfect 100.0%; the rest are below. Open the answer in a popup, or compare it across every model.

Task	Domain	Difficulty	Objective	pass@1	Output
ACC-0002	Australian accounting	medium	10.0%	0.0%	Compare Open
ACC-0003	Australian accounting	easy	90.0%	100.0%	Compare Open
AUSFA-0001	Australian accounting	easy	10.0%	0.0%	Compare Open
AUSFA-0002	Australian accounting	medium	85.0%	100.0%	Compare Open
AUSFA-0004	Australian accounting	medium	0.0%	0.0%	Compare Open
AUSFA-0005	Australian accounting	medium	0.0%	0.0%	Compare Open
AUSFA-0006	Australian accounting	medium	15.0%	0.0%	Compare Open
AUSFA-0009	Australian accounting	hard	0.0%	0.0%	Compare Open
AUSFA-0012	Australian accounting	hard	33.3%	0.0%	Compare Open
AUSFA-0013	Australian accounting	hard	66.7%	0.0%	Compare Open
AUSFA-0014	Australian accounting	hard	0.0%	0.0%	Compare Open
BASQU-0003	Australian accounting	hard	0.0%	0.0%	Compare Open
LAW-0003	Australian law	hard	0.0%	0.0%	Compare Open