Animation Bench tests coding agents on rebuilding web animations, and motion is their weak spot

himanshustwts · x · 2026-10-01

Physera released Animation Bench v1.0, a benchmark arguing that screenshot-parity evaluations can't distinguish visually plausible output from shippable frontend reconstruction. It asks multimodal coding agents to rebuild 48 real web animations from 32 live commercial sites (192 reconstructions), scoring visual, motion, and layout fidelity.

Leaderboard (0-1 reproduction score):

The standout finding: motion scores sit below 0.5 for every model (best: 0.473), while visual scores reach 0.63-0.71 — frontier agents can copy a page's look but still struggle to reproduce scroll, drag, and WebGL-driven behavior. Full task set and side-by-side reconstructions are in the appendix.

Related event: Animation Bench Launches to Test Web Animation Replication(4 posts)→

Original post →

More from coding & agent

coding & agent channel →