Grounding scenario · 2026-08-13

Locate the Search rooms input in Smart home

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

Case IDroom search

390 × 844 · 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 rooms input

Return only data matching the supplied JSON schema. Do not describe your reasoning.
SHA-256 · e9b67c5998c1b5c4ab14d2609b2b66cb452ac1a3ff8dd5e1f37d6f56e45ff0b1
Smart home UI with the the Search rooms input target highlightedExpected
Ground truth: the Search rooms input

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
0.247
Latency
1.46 s
Cost
$0.00034
Raw response
{"point": {"x": 498,  	"y": 147}, "box": {"x": 47, "y": 125, "width": 953, "height": 169}}

Grok 4.5

xAI · x-ai/grok-4.5
Point hit
Format
Valid
Box IoU
0.619
Latency
1.39 s
Cost
$0.0012
Raw response
{"point": {"x": 500, "y": 160}, "box": {"x": 40, "y": 130, "width": 920, "height": 60}}

GPT-5.4

OpenAI · openai/gpt-5.4
Point hit
Format
Valid
Box IoU
0.408
Latency
2.07 s
Cost
$0.0025
Raw response
{"point":{"x":250,"y":152},"box":{"x":18,"y":107,"width":938,"height":50}}

Gemini 3.6 Flash

Google AI Studio · google/gemini-3.6-flash
Point hit
Format
Valid
Box IoU
0.866
Latency
1.19 s
Cost
$0.0021
Raw response
{"point":{"x":500,"y":150},"box":{"x":46,"y":125,"width":908,"height":50}}

GPT-5.6 Sol

OpenAI · openai/gpt-5.6-sol
Point hit
Format
Valid
Box IoU
0.864
Latency
3.15 s
Cost
$0.0064
Raw response
{"point":{"x":500,"y":150},"box":{"x":46,"y":126,"width":908,"height":50}}

GPT-5.6 Luna

OpenAI · openai/gpt-5.6-luna
Point hit
Format
Valid
Box IoU
0.864
Latency
2.18 s
Cost
$0.00014
Raw response
{"point":{"x":500,"y":151},"box":{"x":46,"y":126,"width":908,"height":50}}

Claude Sonnet 5

Anthropic · anthropic/claude-sonnet-5
Point hit
Format
Valid
Box IoU
0.088
Latency
3.55 s
Cost
$0.0028
Raw response
{"point":{"x":195,"y":127},"box":{"x":18,"y":112,"width":354,"height":30}}

Claude Opus 5

Anthropic · anthropic/claude-opus-5
Point miss
Format
Valid
Box IoU
0.000
Latency
3.98 s
Cost
$0.0071
Raw response
{"point":{"x":500,"y":325},"box":{"x":43,"y":283,"width":913,"height":83}}

Gemini 3.1 Pro Preview

Google AI Studio · google/gemini-3.1-pro-preview
Point hit
Format
Valid
Box IoU
0.839
Latency
20.55 s
Cost
$0.0030
Raw response
{"point": {"x": 500, "y": 149}, "box": {"x": 47, "y": 126, "width": 907, "height": 47}}
EN