Grounding scenario · 2026-08-13

Locate the search icon button in Commerce catalog

Every model received the same screenshot, prompt, and structured response contract.

Case IDsearch

1440 × 900 · normalized 0–1000 coordinates

Exact input

Prompt

You are evaluating a user interface screenshot for test automation.

Locate the single UI element described below. Return the best click point and the tight visible bounding box of the complete interactive target. Coordinates use a normalized 0 to 1000 grid, where (0, 0) is the top-left image corner and (1000, 1000) is the bottom-right image corner.

Target: the search icon button

Return only data matching the supplied JSON schema. Do not describe your reasoning.
SHA-256 · 3b327f221bc188bdf0ec28afff760371b1d567344443535e5c68380fb9f7789b
Commerce catalog UI with the the search icon button target highlightedExpected
Ground truth: the search icon button

Model evidence

9 responses

Blue marks the browser-derived target. Orange marks the model’s returned box and point. Format validity checks only the response contract; it does not mean the requested element was found.

Holo3 122B A10B

H Company · holo3-122b-a10b
Point hit
Format
Valid
Box IoU
0.572
Latency
1.73 s
Cost
$0.00070
Raw response
{"point": {"x":923, "y":39}, "box": {"x": 909, "y": 18, "width": 35, "height": 60}}

Grok 4.5

xAI · x-ai/grok-4.5
Point hit
Format
Valid
Box IoU
0.339
Latency
1.45 s
Cost
$0.0038
Raw response
{"point": {"x": 910, "y": 48}, "box": {"x": 895, "y": 32, "width": 35, "height": 35}}

GPT-5.4

OpenAI · openai/gpt-5.4
Point hit
Format
Valid
Box IoU
0.903
Latency
2.16 s
Cost
$0.0060
Raw response
{"point":{"x":923,"y":40},"box":{"x":910,"y":18,"width":28,"height":44}}

Gemini 3.6 Flash

Google AI Studio · google/gemini-3.6-flash
Point hit
Format
Valid
Box IoU
0.879
Latency
1.36 s
Cost
$0.0021
Raw response
{"point":{"x":923,"y":40},"box":{"x":908,"y":19,"width":30,"height":42}}

GPT-5.6 Sol

OpenAI · openai/gpt-5.6-sol
Point hit
Format
Valid
Box IoU
0.701
Latency
3.67 s
Cost
$0.0148
Raw response
{"point":{"x":927,"y":40},"box":{"x":913,"y":18,"width":28,"height":46}}

GPT-5.6 Luna

OpenAI · openai/gpt-5.6-luna
Point hit
Format
Valid
Box IoU
0.968
Latency
2.16 s
Cost
$0.00031
Raw response
{"point":{"x":923,"y":40},"box":{"x":909,"y":18,"width":28,"height":44}}

Claude Sonnet 5

Anthropic · anthropic/claude-sonnet-5
Point miss
Format
Invalid
Box IoU
0.000
Latency
4.32 s
Cost
$0.0054
Raw response
{"point":{"x":1328,"y":36},"box":{"x":1310,"y":21,"width":36,"height":30}}

point must use normalized 0..1000 coordinates. box must be positive and contained in normalized 0..1000 coordinates.

Claude Opus 5

Anthropic · anthropic/claude-opus-5
Point hit
Format
Valid
Box IoU
0.594
Latency
4.12 s
Cost
$0.0135
Raw response
{"point":{"x":922,"y":25},"box":{"x":908,"y":13,"width":29,"height":34}}

Gemini 3.1 Pro Preview

Google AI Studio · google/gemini-3.1-pro-preview
Point hit
Format
Valid
Box IoU
0.141
Latency
3.77 s
Cost
$0.0030
Raw response
{"point": {"x": 923, "y": 40}, "box": {"x": 923, "y": 40, "width": 27, "height": 44}}
EN