LLM Stats (DocVQA) — leaderboard
Metric: Score (%). Source: llm-stats.com. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 VL 7B Instruct | 95.7 |
| 2 | Claude 3.5 Sonnet | 95.2 |
| 3 | Qwen2.5-Omni-7B | 95.2 |
| 4 | Mistral Small 3.2 | 94.86 |
| 5 | Qwen 2.5 VL 32B Instruct | 94.8 |
| 6 | Llama 4 Maverick | 94.4 |
| 7 | Llama 4 Scout | 94.4 |
| 8 | Grok 2 | 93.6 |
| 9 | Nova Pro | 93.5 |
| 10 | Pixtral Large | 93.3 |
| 11 | Phi-4 Multimodal Instruct | 93.2 |
| 12 | GPT-4o | 92.8 |
| 13 | Nova Lite | 92.4 |
| 14 | Pixtral-12B | 90.7 |
| 15 | Llama 3.2 90B Instruct | 90.1 |
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-docvqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.