GDP.pdf evaluates grounded multimodal reasoning over 100 real professional PDF workflows spanning ten domains. Tasks require locating evidence, interpreting tables, charts, forms and diagrams, cross-referencing documents, and avoiding unsupported claims; strict pass rate requires satisfying all task rubric criteria.
Browse the latest scores, model modes, release dates, and parameter sizes for GDP.pdf.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Gemini 3.7 Flash Thinking Level · Medium | 34.00 | 2026-08-13 | Unknown | Closed |
Google reported a GDP.pdf task pass rate of 34.0% for Gemini 3.7 Flash in its official model card on 2026-08-13.
