llava-onevision-qwen2-72B-ov-sft: benchmark results
Provider: LLaVA Team. Access: Open.
Aggregate Rating 1522 ± 46, rank #1957 of 10556 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ColorBench | 51.9 | P&R Overall accuracy (%) | 96.7 |
| KOFFVQA - Hallucination and Robustness | 86 | Score (%) | 94.4 |
| ColorBench - Color Robustness | 80.3 | Color Robustness (%) | 90 |
| KOFFVQA - Relationship | 71 | Score (%) | 82.7 |
| KOFFVQA - Object Attributes | 77.83 | Score (%) | 71.6 |
| KOFFVQA - Commonsense Reasoning | 79.33 | Score (%) | 62.3 |
| KOFFVQA - Recognition | 65 | Score (%) | 45.1 |
| KOFFVQA - Graph and Chart Understanding | 54 | Score (%) | 40.7 |
| KOFFVQA | 54.15 | Overall Score (%) | 38.3 |
| KOFFVQA - Korean Recognition | 5 | Score (%) | 22.8 |
| KOFFVQA - Table Understanding | 18.33 | Score (%) | 18.5 |
| KOFFVQA - Document Understanding | 23 | Score (%) | 15.4 |
Interactive version: theaggregate.ai/model?slug=llava-onevision-qwen2-72b-ov-sft · How It Works · Data refreshed daily, snapshot 2026-11-17.