AlreadyGood.Sign inStart creating

What Veo 3.1 actually changed about motion

We ran the same twelve prompts through Veo 3.0 and 3.1 and scored every camera move. Three prompt patterns got better. One got worse.

A warm, ember-lit frame from the orbit test setVeo 3.10:08
Frame from the orbit test set · 8s · 16:9Rendered with Veo 3.1

Google shipped Veo 3.1 with the usual language — "improved motion coherence", "better prompt adherence" — and the usual absence of anything you could measure. So we measured it. Same twelve prompts, same seeds where the API allows it, three renders each on 3.0 and 3.1, scored blind by two of us on whether the camera did what the prompt asked.

The short version: 3.1 is a meaningfully better model for anything involving a moving camera, and a slightly worse one for hand-held. The long version is below, with the prompts, so you can check our work.

The test set

Twelve prompts, chosen to isolate one camera behaviour each. Four orbits at different speeds, three dollies, two crane moves, two static-camera-moving-subject shots, and one deliberately hand-held. All 8 seconds, all 16:9, all with the same three-word lighting suffix so the model wasn't spending capacity on mood.

Step by stepHow the benchmark was scored
01
Choose promptsTwelve prompts isolate camera behaviours
02
Render both modelsThree renders each on 3.0 and 3.1
03
Score blindTwo scorers judge whether moves landed
04
Resolve disagreementsA third render settles disputed scores
Note: A reproducible test separates camera adherence from visual quality.
Move Prompts 3.0 landed 3.1 landed Change
Orbit 4 5 / 12 11 / 12 +6
Dolly 3 6 / 9 8 / 9 +2
Crane 2 2 / 6 5 / 6 +3
Static, subject moves 2 6 / 6 6 / 6 0
Hand-held 1 3 / 3 1 / 3 −2

"Landed" means both scorers agreed the camera did the thing described, without drifting into a different move partway through. It's a harsh bar — a beautiful render that starts as an orbit and settles into a slow push-in counts as a miss.

Orbits: the headline improvement

On 3.0, orbit prompts were a coin flip. The model understood "orbit" as "the camera should be moving, in a curved sort of way" and would frequently reverse direction at the four-second mark or collapse into a pan. On 3.1, eleven of twelve renders completed a clean partial orbit in the direction we asked, and the twelfth was a near miss rather than a different shot.

The prompt that improved the most was also the plainest one:

Shot recipeOrbit · test 03

A red kite over a foggy harbour at dawn, slow drone orbit clockwise, soft light

Veo 3.18s16:9Cost12 creditsOpen in Studio

Note "clockwise". On 3.0 the direction word was ignored roughly half the time. On 3.1 it was honoured in every render. If you've been avoiding direction words because they seemed to confuse the model, stop — they now do exactly what they say.

Wide shot of an ice field from a slow crane move
Crane test 02 — the move 3.0 could not hold for eight seconds. 3.1 holds it and adds parallax on the foreground ice.

Hand-held got worse, and we think we know why

The one regression is real. Our hand-held prompt ("hand-held, slight natural shake, following a runner along a pier") produced convincingly organic camera movement on 3.0. On 3.1, two of three renders were noticeably too smooth — a stabilised gimbal shot with a sinusoidal wobble laid over it. It reads as synthetic in a way the 3.0 output didn't.

A runner travels along a misty wooden pier, photographed with a natural hand-held feel.
The hand-held look is the one camera behavior that regressed in the test.

The model got better at doing what you ask and worse at doing what you mean. For hand-held, those are different things.

Our guess is that whatever training pushed motion coherence up also pushed the model away from the small, irregular accelerations that make hand-held feel hand-held. It's tunable in post — we got acceptable results by asking for a static shot and adding shake in the editor — but it's a real loss if you were relying on the model for it.

Watch out

If you have hand-held shots in a saved storyboard that rendered well on 3.0, don't batch-regenerate them on 3.1 without checking one first. Studio keeps the previous model available for exactly this reason.

What this means for how you prompt

Three concrete changes to make today:

  1. Use direction words. Clockwise, left-to-right, rising, descending. They were noise on 3.0. They are instructions on 3.1.
  2. Drop the belt-and-braces phrasing. "Slow smooth steady orbit" was a 3.0 habit — piling on adjectives to nudge a reluctant model. On 3.1 "slow orbit" does the job and the extra words occasionally introduce a speed change.
  3. Add shake in the edit, not the prompt. Until Google addresses it, ask for a locked-off or gimbal shot and add hand-held texture in the editor.

The full prompt set is in the CLI as a benchmark you can run against any model:

# runs all twelve camera prompts, three seeds each
$ ag bench camera --models veo-3.1,veo-3 --seeds 3 --out ./camera-bench
# ~34 min, 216 credits
Method

Two scorers, blind to model, disagreements resolved by a third render. Scores and prompts are published in full so the benchmark is reproducible. We'll re-run it on every Veo release and update this post rather than write a new one — check the date in the header.

Keep up

Every model launch, benchmarked.

Same twelve prompts through every new model within days of release. Scores, costs, and the shots that broke — no product announcements dressed up as insight.