SAME-PROMPT BENCHMARK · AUGUST 2026
Best AI Video Model for Camera Motion
Dollies, push-ins, one continuous shot. We gave five models the identical brief on ManifoldGen — here are the actual generations, ranked.
THE EXACT PROMPT EVERY MODEL RAN
One continuous dolly shot pushing through the open door of a cozy late-night ramen shop toward a steaming bowl, steam swirling, shallow depth of field, warm practical lights
WINNER
THE REST OF THE FIELD — SAME PROMPT
| RANK | MODEL | WHY IT PLACED HERE | MEDIAN SPEED* |
|---|---|---|---|
| 1 | Seedance 2 | The only model that holds one unbroken move from street to bowl without a cut. | — |
| 2 | Manifold H3 | Confident push-in with beautiful steam simulation. | 264s |
| 3 | LTX 2 | Smooth move, small spatial jump mid-shot. | 65s |
| 4 | Wan | Steady but slower-feeling dolly. | — |
| 5 | Seedance 2 Fast | Draft-speed version with simpler depth cues. | — |
*Median wall-clock time across this model's completed runs in our harness. Placements are editorial calls made from these exact generations — watch the clips above and disagree with us. Generations for this category are still running.
Making camera motion shots?
Paste your prompt into ManifoldGen. One subscription, every model — pick the winner yourself or let routing do it.