LLaVA-OV-1.5-8B: benchmark results
Provider: LLaVA Team.
Aggregate Rating 1425 ± 44, rank #4907 of 10916 rated models, from 79 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ProactEgoMem - Daily IC - Notification Precision | 16.7 | Score (%) | 91.7 |
| ProactEgoMem - Sci IC - Intervention Precision | 7.1 | Score (%) | 91.7 |
| ProactEgoMem - Sci LT - Intervention Precision | 12.5 | Score (%) | 91.7 |
| ProactEgoMem - Daily IC - Intervention Precision | 8.8 | Score (%) | 83.3 |
| JMMMU-Pro | 31.97 | Overall (percent) | 61.5 |
| JMMMU-Pro - Culture Agnostic | 35.28 | Accuracy (%) | 61.5 |
| JMMMU-Pro - Japanese Art | 34 | Accuracy (%) | 61.5 |
| JMMMU-Pro - Overall | 31.97 | Accuracy (%) | 61.5 |
| VIABench - VQA | 37.3 | Visual question answering score (0-100): answers to question | 57.1 |
| ProactEgoMem - Daily IC - Intervention F1 | 3.5 | Score (%) | 50 |
| ProactEgoMem - Daily LT - Intervention Precision | 7 | Score (%) | 50 |
| ProactEgoMem - Daily ST - QA Accuracy | 21.9 | Score (%) | 45.8 |
Interactive version: theaggregate.ai/model?slug=llava-ov-1-5-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.