V-STaR - Short mLGM: leaderboard

V-STaR short-video mLGM score measures spatio-temporal reasoning on short clips.

Metric: Score. Source: huggingface.co. Saturation forecast: Around February 2027. 14 models tracked.

Top models

#ModelScoreOverall rank
1GPT-4o38.56#741
2Gemini 2.0 Flash32.07#702

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=v-s-tar-short-mlgm · How It Works · Data refreshed daily, snapshot 2026-11-12.