multimodal benchmark
GDP.pdf
GDP.pdf is a knowledge-work vision benchmark that evaluates models on economically valuable professional tasks presented as visual documents (PDFs), testing document-based reasoning, chart and table interpretation, and problem solving without tools.
Updated Aug 7, 2026
Published models5
Registry coverage5
MetricScore
EvidenceB
GDP.pdf leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AN | 81.6% | 100.0% | 5 | C | |
| 2 | OP | 30.7% | 75.0% | 5 | C | |
| 3 | AN | 29.8% | 50.0% | 5 | C | |
| 4 | OP | 24.7% | 25.0% | 5 | C | |
| 5 | OP | 22.7% | 0.0% | 5 | C |
Score distribution
Top published rows on the benchmark's original scale.
GDP.pdf highlights
The top published results on this benchmark's own scale.
What is GDP.pdf?
Definition and scoring fields from the benchmark registry.
GDP.pdf is a knowledge-work vision benchmark that evaluates models on economically valuable professional tasks presented as visual documents (PDFs), testing document-based reasoning, chart and table interpretation, and problem solving without tools.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- GDP.pdf
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- gdp-pdf|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about GDP.pdf.
Which model scores highest on GDP.pdf?
Claude Sonnet 5 is currently ranked first with 81.6%.
What does GDP.pdf measure?
GDP.pdf is a knowledge-work vision benchmark that evaluates models on economically valuable professional tasks presented as visual documents (PDFs), testing document-based reasoning, chart and table interpretation, and problem solving without tools.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
5 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.