Video-MemComp OVO Compression Thresholds - ATR: leaderboard
Video-MemComp v1: streaming evaluation of official development sets. Table 1 mixes reproduced starred rows and results from prior papers; frame sampling and average KV budget differ by system and remain in row identity. Backbone checkpoint revision and decoding are not fully specified; source-qualified systems are retained. This is video QA under cache compression, not an unmodified backbone score. Appendix F identifies Qwen2.5-VL-7B on OVO. These are distinct hyperparameter arms evaluated on the same questions, not independently sampled tasks; preserve every configuration. ATR. Metric: Accuracy (%).
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Video-MemComp Qwen2.5-VL-7B Compression Thresholds [0.70, 0.80] | 68.1 | |
| 2 | Video-MemComp Qwen2.5-VL-7B Compression Thresholds [0.60, 0.85] | 64.66 | |
| 3 | Video-MemComp Qwen2.5-VL-7B Compression Thresholds [0.70, 0.85] | 63.79 | |
| 4 | Video-MemComp Qwen2.5-VL-7B Compression Thresholds [0.80, 0.75] | 63.79 | |
| 5 | Video-MemComp Qwen2.5-VL-7B Compression Thresholds [0.30, 0.60] | 62.93 | |
| 6 | Video-MemComp Qwen2.5-VL-7B Compression Thresholds [0.50, 0.80] | 62.93 | |
| 7 | Video-MemComp Qwen2.5-VL-7B Compression Thresholds [0.80, 0.85] | 62.93 | |
| 8 | Video-MemComp Qwen2.5-VL-7B Compression Thresholds [0.95, 0.90] | 62.93 | |
| 9 | Video-MemComp Qwen2.5-VL-7B Compression Thresholds [0.25, 0.75] | 62.07 | |
| 10 | Video-MemComp Qwen2.5-VL-7B Compression Thresholds [0.30, 0.75] | 62.07 |
Interactive version: theaggregate.ai/benchmark?slug=video-memcomp-ovo-compression-thresholds-atr · How It Works · Data refreshed daily, snapshot 2026-10-27.