LongSCOP Retrieval - Mast3R - Recall@5: leaderboard
LongSCOP v1 referenceframeranking,52LVOcases,4queryframes,candidatesfulltimeline,filterbottom30%registration. Mast3R variant7 suppliesranks/scores/registrationvisualizations topretrainedVLM; nativeRecall@50–1. Reference relevance definedbyobjectivegenerationmetrics; exact combination/perqueryinventorysourceunreported. No videogeneratedquality attribution or guessed aggregate.
Metric: Recall@5 (0–1). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen3.5-27B (LongSCOP Retrieval Run: registration=Mast3R;variant=7) | 0.53 | |
| 2 | Qwen3.5-9B (LongSCOP Retrieval Run: registration=Mast3R;variant=7) | 0.49 |
Interactive version: theaggregate.ai/benchmark?slug=longscop-retrieval-mast3r-recall-5 · How It Works · Data refreshed daily, snapshot 2026-11-12.