LLaVA-OneVision-0.5B: benchmark results
Provider: LLaVA Team. Released 2024-08-05. Access: Open.
Aggregate Rating 1328 ± 24, rank #8200 of 10916 rated models, from 503 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ProactiveBench - QuickDraw | 33.8 | Trajectory accuracy (%) on the partial QuickDraw sketches: m | 100 |
| OpenVLM MMT-Bench - MeViS | 60 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Temporal Ordering | 45 | Score (%) | 97.6 |
| OpenVLM MMT-Bench - Geometrical Relativity | 75 | Score (%) | 96.1 |
| OpenVLM MMT-Bench - Image Matting | 35 | Score (%) | 95.6 |
| OpenVLM MMBench V1.1 EN - Image Topic | 98.9 | Accuracy (%) | 95.2 |
| OpenVLM MMT-Bench - Pixel Recognition | 75 | Score (%) | 94.7 |
| OpenVLM MMT-Bench - Multiple View Image Understanding | 45 | Score (%) | 94.2 |
| OpenVLM MMT-Bench - Color Assimilation | 75 | Score (%) | 93 |
| OpenVLM MMT-Bench - Gaze Estimation | 35 | Score (%) | 93 |
| OpenVLM MMT-Bench - One Shot Detection | 85 | Score (%) | 92.7 |
| OpenVLM MMT-Bench - Order Hallucination | 55 | Score (%) | 92.2 |
Interactive version: theaggregate.ai/model?slug=llava-onevision-0-5b · How It Works · Data refreshed daily, snapshot 2026-11-08.