DocScope - Fact Extraction: leaderboard
Metric: Fact consistency rate (%): share of extracted facts that a Qwen3.6-Plus judge marks consistent with the gold evidence on the correctly retrieved pages, micro-averaged over the answerable questions of the 730-question DocScope test split (human-annotated questions on long, visually rich PDF documents; the model receives the whole document and returns evidence pages, evidence regions, supporting facts and an answer), each stage scored only on the gold pages the model retrieved; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 77.4 |
| 2 | Gemma 4 31B | 73.6 |
| 3 | Claude Sonnet 4.6 | 72.1 |
| 4 | Gemini 3.1 Flash Lite | 70.7 |
| 5 | Gemini 3.1 Pro (Preview) | 68.7 |
| 6 | Qwen 3.6 Plus | 66.4 |
| 7 | Qwen 3.5 27B | 61.3 |
| 8 | GPT-5.4 | 59.4 |
| 9 | Qwen 3.5 397B A17B | 58.7 |
| 10 | Qwen 3 VL 235B A22B | 58.6 |
| 11 | Gemma 4 26B A4B | 53.1 |
Interactive version: theaggregate.ai/benchmark?slug=docscope-fact-extraction · How It Works · Data refreshed daily, snapshot 2026-10-07.