Skip to benchmark content
MotionBenchHosted by Baz Studio
Pilot datasetOne prompt · one trial · 33 routes · not the official Core rankingRead the limits
openai · C

o4-mini

o4-mini
Pilot visual tierB
Human assessment
Post-fix rerun produces a clean real scene and valid 90-frame export.

One diagnostic trial. This is not a durable model capability claim.

o4-mini — MotionBench