LLM Stats (ChartQA): leaderboard
Metric: Score (%). Source: llm-stats.com. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet | 90.8 |
| 2 | Llama 4 Maverick | 90 |
| 3 | Nova Pro | 89.2 |
| 4 | Llama 4 Scout | 88.8 |
| 5 | Qwen 2 VL 72B Instruct | 88.3 |
| 6 | Pixtral Large | 88.1 |
| 7 | Mistral Small 3.2 | 87.4 |
| 8 | Qwen 2.5 VL 7B Instruct | 87.3 |
| 9 | Nova Lite | 86.8 |
| 10 | GPT-4o | 85.7 |
| 11 | Llama 3.2 90B Instruct | 85.5 |
| 12 | Llama 3.2 11B Instruct | 83.4 |
| 13 | Pixtral-12B | 81.8 |
| 14 | Phi-4 Multimodal Instruct | 81.4 |
| 15 | Gemma 3 27B | 78 |
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-chartqa · How It Works · Data refreshed daily, snapshot 2026-09-05.