V-STaR - Long mAM: leaderboard
V-STaR long-video mAM score measures spatio-temporal reasoning on long clips.
Metric: Score. Source: huggingface.co. Saturation forecast: Around April 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.0 Flash | 37.81 | #702 |
| 2 | GPT-4o | 14.86 | #741 |
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-long-mam · How It Works · Data refreshed daily, snapshot 2026-11-12.