VILA1.5-13B: benchmark results
Provider: NVIDIA. Released 2024-05-09. Access: Open.
Aggregate Rating 1356 ± 23, rank #7543 of 10916 rated models, from 503 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Scene Recognition | 85 | Score (%) | 97.3 |
| OpenVLM MMT-Bench - Weather Recognition | 100 | Score (%) | 94.4 |
| OpenVLM MMT-Bench - Relation Hallucination | 85 | Score (%) | 93.9 |
| OpenVLM MMT-Bench - Crowd Counting | 70 | Score (%) | 92.7 |
| Open LMM Reasoning - WeMath - RoteMemorization (Loose) | 20.4 | Accuracy (%) | 91.4 |
| OpenVLM MMT-Bench - Painting Recognition | 90 | Score (%) | 90.8 |
| OpenVLM MMT-Bench - Body Emotion Recognition | 55 | Score (%) | 89.6 |
| OpenVLM MMT-Bench - Counting By Visual Prompting | 45 | Score (%) | 89.1 |
| Open LMM Reasoning - WeMath - RoteMemorization (Strict) | 75.9 | Accuracy (%) | 88.9 |
| OpenVLM MMT-Bench - Emo | 57.5 | Score (%) | 88.3 |
| Open LMM Reasoning - WeMath - InsufficientKnowledge (Loose) | 61.1 | Accuracy (%) | 85.2 |
| OpenVLM MMT-Bench - Building Recognition | 85 | Score (%) | 84.7 |
Interactive version: theaggregate.ai/model?slug=vila1-5-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.