Multimodal & Grounded benchmark
GDP.pdf (tools) leaderboard
GDP.pdf mean criteria pass rate with tools. Every model the catalog carries a published GDP.pdf (tools) value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureMean criteria pass rate with tools
Tasks100 professional document prompts
DifficultyProfessional document reasoning
Published byGDP.pdf
Professional document understanding with a container, standard libraries, and image cropping.
GDP.pdf (tools) ranking
1 model with a published GDP.pdf (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 with tools |
|---|---|---|---|
| 1 |  Claude Opus 5 | Anthropic | 85.5 |
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.