RealWorldQA — leaderboard
RealWorldQA: Evaluates multimodal understanding across image, text, chart, diagram, or cross-modal reasoning tasks.
Metric: RealWorldQA (self-reported). Source: benchmarklist.com. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.7 Plus | 86.9 |
| 2 | Qwen 3.6 Plus | 85.4 |
| 3 | GPT-5.4 | 83.8 |
| 4 | Gemini 3.1 Pro (Preview) | 83.5 |
| 5 | Qwen 3.5 9B | 80.3 |
| 6 | Qwen 3.5 4B | 79.5 |
| 7 | InternVL3-78B | 78 |
| 8 | Claude Opus 4.6 (Max) | 73.9 |
| 9 | GPT-5 Nano | 71.8 |
Interactive version: theaggregate.ai/benchmark?slug=realworldqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.