Layout defect scenario · 2026-08-13

Detect obscured action in Flight pass

Identify the single seeded visible layout defect.

Expected answerobscured actionable control

390 × 844 · 9 model configurations

Exact input

Prompt

You are evaluating a user interface screenshot for objective rendering defects.

Check only for these visible issue categories: viewport_cropping, container_clipping, text_overflow, element_overlap, obscured_actionable_control, or broken_responsive_reflow. Do not report subjective design preferences, copywriting concerns, or accessibility assumptions.

If there is one visible issue, return its category and the tight affected region on a normalized 0 to 1000 grid. If none of these issues is visible, return has_issue=false and null category and region values.

Return only data matching the supplied JSON schema. Do not describe your reasoning.
SHA-256 · 7d8cfe281f4ef9b625bbcc6c89c45236b392624e96c23044e6dcaac1d8d7adb0

Ground truth

Flight pass layout-defect benchmark screenshotExpected defect
Ground truth: obscured actionable control

Model evidence

9 model results

Blue marks the seeded defect region. Orange marks the model’s returned region when available.

Holo3 122B A10B

H Company · holo3-122b-a10b
Correct
Latency
1.69 s
Category
viewport cropping
Localization IoU
0.000
Cost
$0.00038
Attempts
1
                  {"has_issue":true,"category":"viewport_cropping","region":{"x":41,"y":867,"width":959,"height":133}, "description": "The 'Flight update' section is partially cut off at the bottom of the screen, indicating a viewport cropping issue."}
                

Grok 4.5

xAI · x-ai/grok-4.5
Correct
Latency
6.35 s
Category
container clipping
Localization IoU
0.000
Cost
$0.0014
Attempts
1
                  {"has_issue":true,"category":"container_clipping","region":{"x":40,"y":820,"width":920,"height":90},"description":"Blue banner text is clipped by the overlapping red flight update banner at the bottom."}
                

GPT-5.4

OpenAI · openai/gpt-5.4
Correct
Latency
12.15 s
Category
element overlap
Localization IoU
0.000
Cost
$0.0077
Attempts
1
                  {"has_issue":true,"category":"element_overlap","region":{"x":46,"y":852,"width":908,"height":63},"description":"A red update banner overlaps and obscures content within the blue card near the bottom of the screen."}
                

Gemini 3.6 Flash

Google AI Studio · google/gemini-3.6-flash
Correct
Latency
9.48 s
Category
obscured actionable control
Localization IoU
0.984
Cost
$0.0046
Attempts
1
                  {
  "has_issue": true,
  "category": "obscured_actionable_control",
  "region": {
    "x": 46,
    "y": 850,
    "width": 908,
    "height": 65
  },
  "description": "The 'Flight update' banner overlaps and obscures the main action button at the bottom of the screen."
}
                

GPT-5.6 Sol

OpenAI · openai/gpt-5.6-sol
Correct
Latency
10.07 s
Category
obscured actionable control
Localization IoU
0.359
Cost
$0.0087
Attempts
1
                  {"has_issue":true,"category":"obscured_actionable_control","region":{"x":46,"y":869,"width":910,"height":23},"description":"The red flight-update banner overlaps and obscures the lower portion of the blue action button."}
                

GPT-5.6 Luna

OpenAI · openai/gpt-5.6-luna
Correct
Latency
9.53 s
Category
obscured actionable control
Localization IoU
0.978
Cost
$0.00019
Attempts
1
                  {"has_issue":true,"category":"obscured_actionable_control","region":{"x":46,"y":850,"width":908,"height":64},"description":"The red flight update banner visibly covers the lower portion of the blue actionable button beneath it."}
                

Claude Sonnet 5

Anthropic · anthropic/claude-sonnet-5
Correct
Latency
10.05 s
Category
element overlap
Localization IoU
0.000
Cost
$0.0035
Attempts
1
                  {"has_issue":true,"category":"element_overlap","region":{"x":18,"y":718,"width":354,"height":55},"description":"The red 'Flight update' notification banner overlaps the blue 'Check-in' button above it, obscuring its text."}
                

Claude Opus 5

Anthropic · anthropic/claude-opus-5
Incorrect
Latency
12.34 s
Category
element overlap
Localization IoU
0.000
Cost
$0.0089
Attempts
1
                  {"has_issue":true,"category":"element_overlap","region":{"x":46,"y":1808,"width":908,"height":150},"description":"The red 'Flight update' banner overlaps and hides the blue 'Check in' button text at the bottom of the screen."}
                

region must be contained in normalized 0..1000 coordinates. has_issue=true requires a category and normalized region.

Gemini 3.1 Pro Preview

Google AI Studio · google/gemini-3.1-pro-preview
Correct
Latency
17.76 s
Category
element overlap
Localization IoU
0.000
Cost
$0.0033
Attempts
1
                  {"has_issue": true, "category": "element_overlap", "region": {"x": 46, "y": 850, "width": 907, "height": 64}, "description": "The red 'Flight update' banner is overlapping the blue 'Check in' button at the bottom of the screen."}
                
EN