CONTRA LABS / Battle
Six image models made real ads. Each broke differently.
Loading the complete research…
Related research
GPT Image 2 won 41.9% of logo tournaments, and still only half its logos were client-ready
10 brand designers judged GPT Image 2, Nano Banana Pro, MAI Image 2.5, and Meta Muse across 12 logo briefs. The winner is clear, and still only half its logos cleared the client bar.
Contra LabsRead article
Pretty isn’t the same as right: One image model runs away with brief fidelity
Five designers, four criteria, 6,400 blind pairwise ratings. Nano Banana 2 takes first on every brief-fidelity axis while the aesthetics standings invert behind it.
Contra LabsRead article
No model owns “aesthetics”: What 8,000 designer ratings tell us about taste in image models
Five designers, five criteria, 8,000 blind pairwise ratings. Three of the four frontier models land within a few points of each other, and the best model changes depending on which dimension of visual quality you care about.
Contra LabsRead article