Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Multimodal & Grounded benchmark
GDP.pdf mean criteria pass rate without tools. Every model the catalog carries a published GDP.pdf (no tools) value for, ranked by that value.
Professional document understanding over 100 real-world PDFs from ten domains. 3 models in the ModelChoice catalog have a published value.
Each point is a model with a published GDP.pdf (no tools) value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
3 models with a published GDP.pdf (no tools) value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Mean criteria pass rate |
|---|---|---|---|
| 1 | Anthropic | 85.4 | |
| 2 | Anthropic | 83.4 | |
| 3 | DSdots3-note Preview | Dots Studio | 60.7 |
What the benchmark measures and how its value is published, from the source’s own record.
GDP.pdf (no tools) (GDP.pdf mean criteria pass rate without tools) is a multimodal & grounded benchmark published by GDP.pdf. Professional document understanding over 100 real-world PDFs from ten domains. Its evaluation set is described by the source as 100 professional document prompts. The source rates its difficulty as professional document reasoning.
Each model's result is published by GDP.pdf as mean criteria pass rate. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 3 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
All leaderboards · Multimodal & Grounded capability leaderboard
Evidence key: Observed
Rows are ordered by the value GDP.pdf published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.