Animation Bench full leaderboard: GPT-6 Astra leads as motion scores lag
himanshustwts · x · 2026-10-01
Physera published full details of Animation Bench: 4 frontier models, 48 tasks from 32 live commercial websites, 192 reconstructions.
- GPT-6 Astra — 0.594 overall (visual 0.710 / motion 0.473 / layout 0.628), 27 task wins, $3.04/task
- Claude Fable 5.1 — 0.548
- GPT-6 Sol — 0.516, cheapest at $0.45/task
- Claude Opus 5.5 — 0.507
Takeaway: models can mimic appearances but struggle to reconstruct page behavior — motion consistency is the weakest axis across the board. The team focuses on capability gaps in multimodal and commercial settings.
Related event: Animation Bench Launches to Test Web Animation Replication(4 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- 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