LLaVA-Bench — leaderboard
LLaVA-Bench: Evaluates multimodal understanding across image, text, chart, diagram, or cross-modal reasoning tasks.
Metric: Score. Source: huggingface.co. Status: saturation imminent. 234 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 (2025-04-14) | 105.6 |
| 2 | Gemma 3 27B | 103.1 |
| 3 | InternVL3-78B | 100.4 |
| 4 | Grok 2 (1212) | 100 |
| 5 | GPT-4.1 Mini | 99.6 |
| 6 | Gemini 2.0 Flash | 97.7 |
| 7 | Gemini 1.5 Pro | 95.3 |
| 8 | InternVL3-38B | 94.7 |
| 9 | Claude 3.7 Sonnet | 94.4 |
| 10 | Gemma 3 12B | 93 |
| 11 | Gemma 3 4B | 92.5 |
| 12 | Claude 3.5 Sonnet (20241022) | 89.4 |
| 13 | GPT-4.1 Nano | 88.8 |
| 14 | Ovis2-8B | 87 |
| 15 | Llama 3.2 90B Vision Instruct | 86.5 |
Interactive version: theaggregate.ai/benchmark?slug=llava-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.