V-STaR - Medium mLGM: leaderboard

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

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

Top models

#ModelScoreOverall rank
1GPT-4o40.58#343
2Gemini 2.0 Flash40.35#342

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=v-star-medium-mlgm · How It Works · Data refreshed daily, snapshot 2026-10-20.