PLLaVA-7B: benchmark results
Provider: Other.
Aggregate Rating 1460 ± 51, rank #3298 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| FluVid (Video Input) | 0.48 | Spearman rank correlation (SRCC, -1 to 1) between the model' | 50 |
| FluVid (Video Input) - PLCC | 0.45 | Pearson linear correlation (PLCC, -1 to 1) between the model | 37.5 |
| CCTVBench - Balanced Accuracy | 57.38 | Balanced accuracy (%) over all binary video-question instanc | 33.3 |
| CCTVBench | 3.9 | Quadruple accuracy (%): share of question pairs in which the | 11.1 |
| LongVideoBench | 39.2 | Test Total Accuracy (%) | 5.9 |
| TVBench | 34.9 | Average Accuracy | 0 |
Interactive version: theaggregate.ai/model?slug=pllava-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.