UGC questions › Testing ads on Meta

What did Meta's Andromeda update change for ad creative?

TL;DR

Meta's Andromeda update changed the first step in how Meta picks which ads to show. Meta says it improves results and that varied creative now matters more than narrow targeting. But Meta has never said how many ads to run or how it treats ads that look alike. Most Andromeda "rules" you read online are marketers' guesses. In our data, running many copies of one ad didn't help it last longer.

Key findings

  • Andromeda is the first step in Meta's ad system. It narrows tens of millions of ads to a few thousand for each person.
  • Meta reported 8% better ad quality in some groups at launch. In October 2026 it said Andromeda had added 2.4% more Facebook conversions since 2025.
  • Meta has not published a best number of ads, a rule for look-alike ads, or how fast ads now wear out.
  • In our data, running 10 or more copies of one ad idea didn't help it last longer.
  • Advertisers with more different ideas kept ads running a bit longer. Once we compared within the same industry, the gap was too small to be sure.
  • Meta says partnership ads cut the cost of each extra sale by 45% in 20 European tests. Meta ran those tests itself.

What is Meta Andromeda?

TL;DR: Andromeda is the system that makes Meta's first shortlist of ads for each person. A second system then picks the final ad.

Meta's engineering team announced Andromeda on December 2, 2024. It handles "retrieval", the first stage of Meta's ad system. For each person and each moment, it picks a few thousand candidate ads from tens of millions. Later stages rank that shortlist and choose the ad you see (Meta Engineering).

Meta said the new system could run models 10,000 times more complex than before, on NVIDIA Grace Hopper chips and Meta's own MTIA chips. It reported a 6% gain in recall, which measures how often the right ads make the shortlist, and an 8% gain in ad quality "on selected segments". It didn't say which segments or how quality was measured.

Andromeda isn't a setting you turn on. It runs behind every campaign, alongside other models Meta has built since, like GEM, its large ads model, and Lattice.

What has Meta actually said about Andromeda?

TL;DR: Meta has told us what Andromeda is and shared a few results. Its main advice is to make more kinds of ads.

DateWhat Meta saidSource
December 2024Andromeda launched as the retrieval stage. 10,000x model complexity, +6% recall, +8% ad quality on selected segments. Meta expects the number of ads to grow a lot with AI tools.Meta Engineering
March 2025Andromeda, Lattice and GEM described together, with gains of up to 6% in conversions for Lattice and up to 5% on Reels for GEMMeta for Business
April 2025The focus "has shifted from niche targeting to creative diversification". Meta urges advertisers to vary their creative.Meta for Business
September 2026A Meta spokesperson called creative variety a "longstanding best practice" and declined to detail how its models treat individual adsMarketing Brew
October 2026The next version of Andromeda handles over a billion ads per second and has added 2.4% more Facebook conversions since 2025Meta Engineering

Every performance number in this table comes from Meta. We found no independent test of Andromeda's effect on advertisers' results.

What has Meta never said?

TL;DR: Meta hasn't said how many ads to run, how it handles look-alike ads, or how fast ads wear out now. Anyone who gives you exact numbers is guessing.

These are the most common Andromeda claims, with what Meta has actually said about each.

ClaimWho says itDoes Meta say it?
"Creative is the new targeting"Many agencies and consultantsClose: Meta says focus shifted from niche targeting to creative variety
"Run 10 to 50 ads per ad set"Ad tools and agencies, with numbers from 6 to 50No. Meta has given no number
"Similar ads are grouped into one 'Entity ID' and only one gets shown"Ad tools and agenciesNo. One tool vendor admits "Entity ID" isn't Meta's term. Meta declined to confirm how it treats similar ads.
"Variety beats volume"Agencies and MetaPartly. Meta says to vary creative, and also expects ad volume to grow.
"Ads wear out faster now"UGC vendors and agenciesNo published rate
"Use broad targeting only"Some consultantsMeta pushes automation, but hasn't said "only"
"Hooks matter more than format"AgenciesNo
"UGC wins under Andromeda"UGC sellers, including usNo. Meta publishes creator numbers only for partnership ads.

We sell UGC ads, so the last row is a claim we'd like to be true. We can't find evidence for it, so we won't make it.

The "similar ads" idea is the one most worth understanding. It makes sense that a system choosing from tens of millions of ads would treat near-copies as one idea. But Meta hasn't published how it decides two ads are "too similar", or what happens next. Thresholds like "60% similar" have no Meta source that we could find.

Do more copies of one ad help under Andromeda?

TL;DR: No. In our data, ad ideas run as 10 or more near-copies didn't last longer than ideas run as a single ad.

We tracked 1,368 Meta video ads from 70 advertisers from launch, including ads that were later switched off. We grouped ads into "concepts": the same advertiser, the same opening copy and the same video length.

Concept run asAdsAdvertisersStill running at 90 days
A single ad5206068%
10 or more versions1321132%

Within the same advertiser, there was no real difference (hazard ratio 0.95, 95% CI 0.64 to 1.42). Relaunching a concept later didn't help either (53% against 63% at 90 days). Our part 2 run-length study has the full tables.

So the idea of "make 30 versions of the same ad and let Meta sort it out" isn't backed by this data. That fits Meta's own advice to vary creative, rather than copy it.

Does more creative variety keep ads running longer?

TL;DR: Maybe a little. Advertisers with more different ideas kept ads longer, but the gap mostly went away once we compared within the same industry.

For this guide, we ran a new cut. We took the 43 advertisers in our launch data with 10 or more ads, counted how many distinct concepts each ran per 10 ads, and split them into thirds.

Advertisers grouped by varietyAdvertisersAdsStill running at 90 days95% CI
Least varied third1547652%29% to 74%
Middle third1446553%25% to 85%
Most varied third1431279%65% to 93%

The most varied advertisers kept ads running 28 points more often (CI +1 to +55). Once we split advertisers into thirds within each industry, the gap fell to 16 points (CI -21 to +55), which is too uncertain to call. Variety in video length showed no pattern at all.

Read this as a weak lean in the direction Meta suggests, not proof. It's 43 advertisers, run length isn't profit, and our "concept" measure uses copy and length, not what the video looks like. All our ads also launched in 2026, after Andromeda rolled out, so we can't compare before and after.

What do partnership ads do under Andromeda?

TL;DR: Meta says partnership ads lowered the cost of each extra sale in its own tests. Meta ran those tests, and some popular numbers have no clear source.

Partnership ads run under both the brand's and a creator's name. Meta's numbers on them:

ClaimSourceHow solid
45% lower median cost per extra sale and 35% higher extra return, when partnership ads were at least 30% of a campaign's adsMeta white paper, October 2026, 20 lift studies in Europe, January to June 2025, at 92% confidence (PPC Land summary)Meta-run; we read a summary, not the paper
19% lower cost per result and 13% higher click-throughWidely repeated, credited to MetaWe couldn't find Meta's original, and accounts of where it came from conflict

Lift studies compare people who could see the ads with a held-out group who couldn't, which makes them stronger than most ad stats. But 92% confidence is below the usual 95% bar, and Meta is grading its own product.

In our run-length data, partnership ads didn't last longer than brand-page ads (54% against 61% at 90 days, a gap our sample is too small to judge). Our guide to Spark Ads, partnership ads and whitelisting covers how to set them up, including ad codes and creator permissions.

What should you change because of Andromeda?

TL;DR: Make different ideas, not more copies. Keep your setup simple, and don't trust anyone selling exact numbers.

  1. Make different concepts. Change the angle, the person, the setting or the offer. A new caption on the same video isn't a new idea.
  2. Don't flood one idea with copies. In our data, 10+ versions of one concept didn't help it last.
  3. Size tests to your budget, not to a rule. No one has published a correct number of ads per ad set. Our guide to how many creatives to test shows how to work it out from your budget.
  4. Keep the structure simple. Meta's tools work best with enough conversions per ad set, so avoid splitting a small budget across many ad sets. Our testing guide covers the two setups we use.
  5. Judge results against your own industry. Industry predicted how long ads ran far better than any creative rule we tested.
  6. Test partnership ads, and measure them yourself. Meta's results are encouraging, and they come from Meta.

What can't anyone prove yet?

TL;DR: No one outside Meta can see how Andromeda treats your ads. Everything else is careful guessing, including ours.

  • How Meta groups look-alike ads. Meta hasn't published it.
  • How many ads an ad set needs. No data links a count to better results.
  • Whether ads now wear out faster. That needs data from before 2025, and nobody has published a fair comparison.
  • How much of Meta's reported gains reach a given advertiser. Meta's figures range from 1.4% to 18.9% depending on the model and the measure, and none is per-advertiser.

We'll compare a second snapshot of our ad data in December to see whether ads are being switched off sooner.

What are the limits of this guide?

TL;DR: Our data shows how long ads run, not sales. All the ads we tracked started after Andromeda began.

  • Run length isn't performance. Meta shows no spend or results for US commercial ads, so a long run means the advertiser kept paying.
  • No before-and-after. Our launch cohorts started in March to April and June to July 2026.
  • Small advertiser count. The variety cut uses 43 advertisers, so most confidence intervals are wide.
  • Our "concept" is a proxy. It groups ads by copy and video length, so it can't see visual similarity the way Meta might.
  • Meta's numbers are Meta's. We report them as Meta states them and label secondary summaries.

Sources

On Google

See more of She Converts in your search results

Add us as a preferred source and Google shows our UGC ad research more often in Top Stories and AI answers.

Add as preferred source

Want to see what this looks like for your ads?

Book a 30-minute call. We review your current ads and your offer and see if we're a fit. No retainer required.

Book a Call