Skip to content

Galaxy AI photo edits leave the fewest flaws in Which? tests

In a Which? lab comparison of three phones, Samsung's generative photo editing performed best across 18 different test photos. Its edits left the fewest distracting flaws.

  • 1 for a person

    Users get cleaner photo edits with fewer distracting flaws, a convenience.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

found, the grade of this recordstudiedreportedclaimed

An independent assessment report supports the benefit.

Compared with

Object removal on the Apple iPhone 16 Pro Max and the Google Pixel 9 Pro XL in the same comparison. Measured.

The system’s part
Not isolated. Which? tested the feature directly, so the edits that it judged were the tool's own output. It compared three phones' AI editors with one another and did not compare them with editing by hand. The article calls the feature AI-powered and generative but does not describe the model behind it.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome
Benefit type
Improved Task Accuracy
System
Samsung generative photo editing on the Galaxy S25 Ultra (Galaxy AI)
Made by
Samsung Electronics
Used by
Samsung Electronics (built into Galaxy S25 Ultra software)
Where
United Kingdom (Which? lab tests)
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Thinking Creatively
Collections
Scrutiny and findings, Cross-border records
Last revised
1 November 2026

Sources

  1. Assessment report, by authors with no tie to the system.

    Which? (Adam Speight). Apple vs Google vs Samsung: which phone has the best AI? 1 August 2025. Which? tested the phones' AI features side by side in its labs. Section on photo, video and image tools, magic editor test.

    In a comparison across 18 different test photos, the Samsung Galaxy S25 Ultra performed best. Its edits showed the fewest distracting flaws in the final image, leaving it the cleanest.
    In our lab tests, Samsung's generative photo editing performed best, removing unwanted objects from pictures, while leaving the cleanest results with the fewest visual flaws.

Details

AI system

Workflow

Which? Compared the object-removal edits of three phones across 18 different test photos in its labs. Samsung's tool removed unwanted objects and could also move, resize and generate objects from a sketch.

Relation to AI

Which? Tested the feature directly, so the edits that it judged were the tool's own output. It compared three phones' AI editors with one another and did not compare them with editing by hand. The article calls the feature AI-powered and generative but does not describe the model behind it.

Follow-up

Conditions for replication

The phone must support Galaxy AI, which Which? Lists for the Galaxy S23 series and newer S series devices and the Galaxy Z Flip/Fold 5 series and newer. Which? Reports that Samsung has said that the AI features are free only until the end of 2025.

Entry details

Sector

Consumer technology (photo editing).

Purpose

Samsung built the Galaxy S25 Ultra's generative photo editing to remove unwanted objects from photos and to move, resize and generate objects.

31 more questions not yet checked

model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Galaxy AI photo edits leave the fewest flaws in Which? tests (AIBD-1052). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1052.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions