RepProbe Synthetic - OBO Many: leaderboard
RepProbe Synthetic - OBO Many. Generalist video-language models; counts 1–20, predictions clipped 0–40; Few 1–6, Mid 7–13, Many 14–20. Reported metric: OBO Many (%). Primary published table, with source configuration boundaries preserved.
Metric: OBO Many (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Cosmos-Reason2-8B | 0 | |
| 2 | Qwen3-VL-8B | 0 | |
| 3 | Video-R1-7B | 0 | |
| 4 | VideoChat-R1.5-7B | 0 | |
| 5 | LongVILA-R1-7B | 0 | |
| 6 | InternVL3.5-8B | 0 | |
| 7 | LLaVA-OneVision-7B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=repprobe-synthetic-obo-many · How It Works · Data refreshed daily, snapshot 2026-10-16.