OCR-Robust — leaderboard
Metric: OCR1.0 Clean (self-reported). Source: benchmarklist.com. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 80.71 |
| 2 | Qwen 3 VL 8B (Thinking) | 79.67 |
| 3 | Qwen 3 VL 4B (Thinking) | 78.63 |
| 4 | GPT-5.2 | 74.69 |
| 5 | Qwen 3 VL 32B Instruct | 72.82 |
| 6 | Llama 4 Scout | 67.84 |
| 7 | GPT-5.1 | 60.58 |
| 8 | InternVL3.5-8B | 57.26 |
| 9 | Qwen 3 VL 8B Instruct | 54.15 |
| 10 | Qwen 3 VL 4B Instruct | 49.79 |
Interactive version: theaggregate.ai/benchmark?slug=ocr-robust · How the rankings work · Data refreshed daily, snapshot 2026-07-22.