HeyGen and Kaggle launch Code2Video Bench for motion graphics code generation
MeganRisdal · x · 2026-09-22
Kaggle and HeyGen introduce Code2Video Bench, a standardized benchmark measuring whether frontier coding models can turn natural-language creative briefs into deterministic, high-quality motion graphics code (HyperFrames). Static image benchmarks and traditional video evals can't test temporal control of animation timing and asset placement. Models receive commercial-grade briefs (e.g. a 6.8s Figma-style product hook with zoom) and their code must be executable and human-preferred. HeyGen argues companies building such tools should open-source rigorous evals to define what "good" looks like, with the Kaggle team collaborating on the benchmark and a technical deep dive.
Related event: HyperFrames Partners with DeepMind and Kaggle on Code2Video Bench(3 posts)→
More from Models
- Xiaomi open-sources MiMo-V2.6 omni-modal models, topping open-model index at 46.32 — victormustar · 2026-09-22
- SemiAnalysis says open source is dying, yet 20+ open models shipped in the past month — _lewtun · 2026-09-22
- Grok 4.7 posts 59% recall on defensive cyber bench at half the cost of rivals — andreamichi · 2026-09-22
- Grok 4.7 jumps from #9 to #3 on BuildingBench with 0.783, 66% cheaper than Fable 5.1 — ZhitingHu · 2026-09-22
- Jev explained: why the AI community's new favorite isn't a traditional LLM — multiply_matrix · 2026-09-22
- LLMs excel at 1-token output — dev proposes replacing low/medium/high reasoning tiers with token counts — arkuto · 2026-09-22