LLaVA-OneVision-72B (SI): benchmark results
Provider: LLaVA Team. Released 2024-08-06. Access: Open.
Aggregate Rating 1508 ± 20, rank #2233 of 10916 rated models, from 252 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LMM Reasoning - WeMath - InadequateGeneralization (Loose) | 17.1 | Accuracy (%) | 100 |
| OpenVLM MME - Position | 178.3 | Score | 99.6 |
| OpenVLM MMBench V1.1 EN - Identity Reasoning | 100 | Accuracy (%) | 99.1 |
| OpenVLM MMBench V1.1 EN - Nature Relation | 95.7 | Accuracy (%) | 98.8 |
| OpenVLM MMBench V1.1 CN - Nature Relation | 95.7 | Accuracy (%) | 98.2 |
| OpenVLM MMBench V1.1 CN - Identity Reasoning | 100 | Accuracy (%) | 97.9 |
| OpenVLM MME - Numerical Calculation | 177.5 | Score | 97 |
| OpenVLM MMBench V1.1 EN - AR | 90.2 | Accuracy (%) | 95.9 |
| OpenVLM MMBench V1.1 CN - Function Reasoning | 95.6 | Accuracy (%) | 95.4 |
| OpenVLM MMBench V1.1 EN - Future Prediction | 85.3 | Accuracy (%) | 95.2 |
| OpenVLM MME - Perception | 1735.5 | Score | 94.9 |
| OpenVLM MMBench V1.1 CN - RR | 84.1 | Accuracy (%) | 94.5 |
Interactive version: theaggregate.ai/model?slug=llava-onevision-72b-si · How It Works · Data refreshed daily, snapshot 2026-11-08.