VideoLVR Paper - LongVideo-Reason: leaderboard
VideoLVR compares video reasoning models on visual understanding, temporal reasoning and long-video questions. Accuracy (%).
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around January 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 76.4 | #415 |
| 2 | Qwen 2.5 VL 7B Instruct | 71.2 | #649 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=videolvr-paper-longvideo-reason · How It Works · Data refreshed daily, snapshot 2026-10-29.