gpt-5.6-luna
gpt-5.6-luna (OpenAI) scored 80.4% composite across 87 tasks. This run covers Australian accounting, Animation, Auth screens, Dashboards, Australian law, Marketing pages, Programming, SVG and graphics, svg-scene, UI components, Websites. Published 2026-07-09.
API single-shotHigh reasoning
Composite
80.4%
95% CI 72.8% - 87.7%
Est. cost
$1.2428
USD
Tokens
237,201
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.
svg-scene
1 task
52.1%
judge
52.1%
composite
Animation
2 tasks
69.8%
judge
69.8%
composite
Australian law
5 tasks
70.0%
composite
Australian accounting
23 tasks
70.8%
composite
Websites
15 tasks
71.1%
composite
Auth screen
1 task
79.2%
judge
79.2%
composite
Dashboard
1 task
81.2%
judge
81.2%
composite
Marketing page
1 task
83.3%
judge
83.3%
composite
UI components
19 tasks
88.8%
composite
SVG and graphics
13 tasks
94.2%
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.
53 results
Objective tasks
Programming, Australian legal and accounting, graded by execution. 22 of 34 scored a perfect 100.0%; the rest are below. Open the answer in a popup, or compare it across every model.