DocScope — leaderboard
Metric: ACC All (self-reported). Source: benchmarklist.com. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 78.9 |
| 2 | Claude Opus 4.7 | 76 |
| 3 | Claude Sonnet 4.6 | 70.5 |
| 4 | Gemini 3.1 Flash Lite | 68.1 |
| 5 | Qwen 3.6 Plus | 66.8 |
| 6 | Qwen 3.5 27B | 66.4 |
| 7 | Qwen 3.5 397B A17B | 63.8 |
| 8 | Qwen 3.5 122B A10B | 63.6 |
| 9 | GPT-5.4 | 62.7 |
| 10 | Gemma 4 31B | 59.4 |
| 11 | Qwen 3 VL 235B A22B | 51.4 |
| 12 | Gemma 4 26B A4B | 34.4 |
Interactive version: theaggregate.ai/benchmark?slug=docscope · How the rankings work · Data refreshed daily, snapshot 2026-07-22.