ShareGPT4V-7B: benchmark results
Provider: LLaVA Team. Released 2024-01-08. Access: Open.
Aggregate Rating 1313 ± 34, rank #8482 of 10916 rated models, from 419 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| FAQ (Deepfake Forensics) - Facial Perception | 73.8 | Accuracy (%) on FAQ's Level 1 facial-perception questions: f | 100 |
| OpenVLM MMT-Bench - Deepfake Detection | 70 | Score (%) | 98.3 |
| OpenVLM MMT-Bench - 3D Indoor Recognition | 50 | Score (%) | 96.4 |
| OpenVLM MMT-Bench - Geometrical Relativity | 75 | Score (%) | 96.1 |
| OpenVLM MME - Scene | 167.2 | Score | 95.7 |
| OpenVLM MMT-Bench - 3D | 57.5 | Score (%) | 95.1 |
| OpenVLM MMT-Bench - Scene Emotion Recognition | 65 | Score (%) | 93.2 |
| OpenVLM MMT-Bench - Color Assimilation | 75 | Score (%) | 93 |
| OpenVLM MME - Celebrity | 170 | Score | 92.3 |
| OpenVLM MMT-Bench - VI | 64.9 | Score (%) | 89.6 |
| OpenVLM MMT-Bench - Point Tracking | 80 | Score (%) | 88.6 |
| OpenVLM MMT-Bench - Scene Recognition | 80 | Score (%) | 88.1 |
Interactive version: theaggregate.ai/model?slug=sharegpt4v-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.