llava-onevision-qwen2-7B-si-hf: benchmark results
Provider: LLaVA Team. Access: Open.
Aggregate Rating 1450 ± 37, rank #3841 of 10552 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CoreCognition Image + Video Intentionality | 77.02 | Accuracy (%) | 69.7 |
| V-DyKnow - Visual Entity Recognition | 80 | Accuracy (%) of naming the entity depicted in each V-DyKnow | 62.5 |
| CoreCognition Image + Video Permanence | 41.91 | Accuracy (%) | 61.3 |
| CoreCognition Image + Video Spatiality | 42.39 | Accuracy (%) | 57.6 |
| CoreCognition Image + Video Perspective | 31.52 | Accuracy (%) | 47.1 |
| CoreCognition Image + Video Continuity | 55.52 | Accuracy (%) | 40.8 |
| CoreCognition Image + Video Conservation | 42.64 | Accuracy (%) | 39.5 |
| CoreCognition Image + Video Perceptualconstancy | 62.21 | Accuracy (%) | 39.5 |
| MCSBench - L3 | 20.61 | Accuracy (%) | 39.5 |
| CoreCognition Image + Video Intuitivephysics | 51.52 | Accuracy (%) | 38.7 |
| CoreCognition Image + Video Hierarchy | 54.29 | Accuracy (%) | 37 |
| CoreCognition Image + Video Mean | 50.84 | Accuracy (%) | 37 |
Interactive version: theaggregate.ai/model?slug=llava-onevision-qwen2-7b-si-hf · How It Works · Data refreshed daily, snapshot 2026-11-16.