Browse renders
Filter by model or shot. Compare and vote.
How it sorts
Within each test: highest complete AI rating, then lower historical cost. Partial panels stay unranked by rating. Lowest cost reverses that priority. Unknown values follow known ones. Ranges use their upper estimate. Human votes stay separate.
Video uses USD per delivered minute. Images use USD per generation until complete spend and human usability checks establish cost per usable image. Failed submissions and retries stay in the test history. Fees and taxes are unconfirmed.
Maggie · MiniMax H3 Max · Nano Banana2.1 source
Believable AI presenter
Maggie · MiniMax H3 Max · Nano Banana Pro source
Believable AI presenter
Maggie · MiniMax H3 · photographic frame
Believable AI presenter
Maggie · MiniMax H3 · less cosmetic frame
Believable AI presenter
Maggie · MiniMax H3 · less cosmetic frame · native 2K
Believable AI presenter
Maggie · Early MiniMax H3 Max
Believable AI presenter
Maggie · Original phone image → MiniMax
Believable AI presenter
Maggie · MiniMax H3 Max — matched pair
Believable AI presenter
WheelOS · shot 3 · Intro lip-sync · fallback
A complete AI story production
WheelOS · shot 3 · Lip-sync test
A complete AI story production
Ordering stays within each test and score method. Shots and settings vary; this is not a model leaderboard.