CC-OCR V2 — leaderboard
Metric: Average (self-reported). Source: benchmarklist.com. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 Plus | 75.77 |
| 2 | Qwen 3.5 Plus (2026-04-20) | 73.03 |
| 3 | Seed 2.0 Pro | 72.15 |
| 4 | Gemini 3.1 Pro (Preview) | 70.17 |
| 5 | Qwen 3.5 9B | 66.61 |
| 6 | Gemini 3.1 Flash | 61.36 |
| 7 | Claude Sonnet 4.6 | 59.6 |
| 8 | Claude Opus 4.6 | 58.58 |
| 9 | GPT-5.4 | 56.43 |
| 10 | InternVL3.5-8B | 47.83 |
| 11 | Step3 VL 10B | 41.66 |
Interactive version: theaggregate.ai/benchmark?slug=cc-ocr-v2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.