LLaVA-Next-Llama3: benchmark results
Provider: LLaVA Team. Released 2024-05-10. Access: Open.
Aggregate Rating 1368 ± 35, rank #7224 of 10916 rated models, from 443 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Deepfake Detection | 70 | Score (%) | 98.3 |
| OpenVLM MMT-Bench - MIA | 85 | Score (%) | 98.3 |
| OpenVLM MMT-Bench - Geometrical Relativity | 75 | Score (%) | 96.1 |
| OpenVLM MMT-Bench - Table Structure Recognition | 100 | Score (%) | 94.7 |
| OpenVLM MMT-Bench - Depth Estimation | 80 | Score (%) | 93.7 |
| OpenVLM MMT-Bench - Salient Object Detection RGBD | 60 | Score (%) | 93.4 |
| OpenVLM MMT-Bench - Traffic Participants Understanding | 65 | Score (%) | 92.5 |
| OpenVLM MMT-Bench - MeViS | 45 | Score (%) | 91.3 |
| OpenVLM MMT-Bench - Spot The Similarity | 90 | Score (%) | 90.8 |
| OpenVLM MMT-Bench - Writing Poetry From Image | 65 | Score (%) | 90 |
| OpenVLM MME - Existence | 200 | Score | 89.7 |
| OpenVLM MME - Scene | 164.5 | Score | 89.3 |
Interactive version: theaggregate.ai/model?slug=llava-next-llama3 · How It Works · Data refreshed daily, snapshot 2026-11-08.