Animation Bench tests 4 frontier models on rebuilding real web animations
himanshustwts · x · 2026-10-01
Physera launched Animation Bench, the first benchmark evaluating frontier coding agents on web animation reconstruction: 4 models, 48 tasks from 32 real commercial websites, 192 reconstructions, scored on visual similarity, motion consistency, and layout correctness.
Key finding: motion consistency is often incomplete or missing — current evals can't distinguish screenshot parity from shippable frontend reconstruction.
Leaderboard: GPT-6 Astra tops at 0.594 (motion only 0.473), Claude Fable 5.1 scores 0.548, GPT-6 Sol 0.516 ($0.45/task), Claude Opus 5.5 last at 0.507.
Related event: Animation Bench Launches to Test Web Animation Replication(4 posts)→
More from coding & agent
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16
- JPMorgan shows Jarvis, its internal agent assembly line, at Interrupt NYC — LangChain · 2026-11-16
- Dev clarifies: Apple doesn't ban feature flags, only fooling App Review — talkaboutdesign · 2026-11-16
- Antigravity Matches Claude Cowork in Tests, While Gemini Tasks' Purpose Remains Unclear — sebajun2 · 2026-11-16
- One 16GB GPU runs songs, voice, images, 720p video and local RAG — all offline and open source — llama-of-death · 2026-11-16