LLaVA-OneVision-7B (SI): benchmark results
Provider: LLaVA Team. Released 2024-08-05. Access: Open.
Aggregate Rating 1431 ± 20, rank #4623 of 10916 rated models, from 525 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Salient Object Detection RGBD | 75 | Score (%) | 100 |
| OpenVLM MMT-Bench - Rock Recognition | 80 | Score (%) | 98.3 |
| OpenVLM MMBench V1.1 CN - Social Relation | 91.2 | Accuracy (%) | 98.1 |
| OpenVLM MMT-Bench - Lesion Grading | 85 | Score (%) | 97.3 |
| OpenVLM MMT-Bench - Handwritten Text Recognition | 100 | Score (%) | 96.6 |
| OpenVLM MMT-Bench - Disease Diagnosis | 95 | Score (%) | 96.4 |
| OpenVLM SEEDBench IMG - Visual Reasoning | 82.5 | Accuracy (%) | 95.8 |
| OpenVLM MMT-Bench - Human Object Interaction Recognition | 90 | Score (%) | 95.6 |
| OpenVLM MMT-Bench - Scene Emotion Recognition | 65 | Score (%) | 93.2 |
| OpenVLM MMT-Bench - Crowd Counting | 70 | Score (%) | 92.7 |
| OpenVLM MMT-Bench - MedU | 80 | Score (%) | 91.7 |
| OpenVLM MMBench V1.0 CN - RR | 82 | Accuracy (%) | 90 |
Interactive version: theaggregate.ai/model?slug=llava-onevision-7b-si · How It Works · Data refreshed daily, snapshot 2026-11-08.