LLaVA-Next-Interleave-7B-DPO: benchmark results
Provider: LLaVA Team. Released 2024-07-10. Access: Open.
Aggregate Rating 1359 ± 33, rank #7479 of 10916 rated models, from 448 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM Q-Bench - How (Distortion) | 68.8 | Accuracy (%) | 98.7 |
| OpenVLM MMT-Bench - Multiple View Image Understanding | 45 | Score (%) | 94.2 |
| OpenVLM MMT-Bench - Point Tracking | 85 | Score (%) | 93.9 |
| OpenVLM MMT-Bench - Relation Hallucination | 85 | Score (%) | 93.9 |
| OpenVLM MMT-Bench - Shape Recognition | 95 | Score (%) | 93.7 |
| OpenVLM MMT-Bench - Gaze Estimation | 35 | Score (%) | 93 |
| OpenVLM AI2D - Volcano | 100 | Accuracy (%) | 92.8 |
| OpenVLM MMT-Bench - CIM | 71.7 | Score (%) | 92.2 |
| OpenVLM MMT-Bench - Temporal Ordering | 40 | Score (%) | 92 |
| OpenVLM MMT-Bench - Artwork Emotion Recognition | 60 | Score (%) | 91.7 |
| OpenVLM MMT-Bench - GUI Install | 55 | Score (%) | 90 |
| OpenVLM Q-Bench - How (In-context Distortion) | 67.8 | Accuracy (%) | 85.1 |
Interactive version: theaggregate.ai/model?slug=llava-next-interleave-7b-dpo · How It Works · Data refreshed daily, snapshot 2026-11-08.