LLaVA-OV-72B: benchmark results
Provider: LLaVA Team.
Aggregate Rating 1537 ± 51, rank #1869 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SYNCR - Object Re-identification | 50 | Exact-match accuracy (%) on the SYNCR Object Re-identificati | 94.1 |
| SYNCR - Multi-Angle Synchronization | 62 | Exact-match accuracy (%) on the SYNCR Multi-Angle Synchroniz | 88.2 |
| SYNCR - Object Counting | 65 | Exact-match accuracy (%) on the SYNCR Object Counting task ( | 88.2 |
| SYNCR - Route Planning | 33.5 | Exact-match accuracy (%) on the SYNCR Route Planning task (p | 88.2 |
| SYNCR | 41.7 | Average exact-match accuracy (%) over the eight SYNCR tasks, | 76.5 |
| SYNCR - Numerical Comparison | 28 | Exact-match accuracy (%) on the SYNCR Numerical Comparison t | 58.8 |
| SYNCR - Sequential Ordering | 37 | Exact-match accuracy (%) on the SYNCR Sequential Ordering ta | 52.9 |
| SYNCR - Spatial Measurement | 41.5 | Exact-match accuracy (%) on the SYNCR Spatial Measurement ta | 44.1 |
| VisualPuzzles | 30.8 | Overall Accuracy (%) | 32.4 |
| TokenSwap-Bench (Image-Interleaved) | 45.1 | Accuracy (%; 1,516 MMLU questions in which visualizable conc | 19.5 |
Interactive version: theaggregate.ai/model?slug=llava-ov-72b · How It Works · Data refreshed daily, snapshot 2026-11-08.