multimodal benchmark
GDP.pdf Leaderboard
GDP.pdf is a multimodal benchmark that evaluates models on professional tasks presented as visual documents (PDFs).
Updated Oct 23, 2026
Models14
Model coverage14
MetricScore
EvidenceB
GDP.pdf Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score81.60% | Percentile100.00% | Participants14 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score35.00% | Percentile92.31% | Participants14 | EvidenceC | Evaluated |
| Rank03 | ModelGO | Score34.00% | Percentile84.62% | Participants14 | EvidenceC | Evaluated |
| Rank04 | ModelME | Score33.20% | Percentile76.92% | Participants14 | EvidenceC | Evaluated |
| Rank05 | ModelME | Score33.20% | Percentile69.23% | Participants14 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score32.00% | Percentile61.54% | Participants14 | EvidenceC | Evaluated |
| Rank07 | ModelME | Score30.80% | Percentile53.85% | Participants14 | EvidenceC | Evaluated |
| Rank08 | ModelME | Score30.80% | Percentile46.15% | Participants14 | EvidenceC | Evaluated |
| Rank09 | ModelOP | Score30.70% | Percentile38.46% | Participants14 | EvidenceC | Evaluated |
| Rank10 | ModelAN | Score29.80% | Percentile30.77% | Participants14 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score24.70% | Percentile23.08% | Participants14 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score22.70% | Percentile15.38% | Participants14 | EvidenceC | Evaluated |
| Rank13 | ModelMI | Score20.80% | Percentile7.69% | Participants14 | EvidenceC | Evaluated |
| Rank14 | ModelMA | Score18.60% | Percentile0.00% | Participants14 | EvidenceC | Evaluated |
GDP.pdf Highlights
The leading models and scores on this benchmark.
GDP.pdf Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for GDP.pdf
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is GDP.pdf?
What GDP.pdf measures and how its scores work.
GDP.pdf is a knowledge-work vision benchmark focused on document-based reasoning and problem solving with visual documents.
It measures document-based reasoning, chart and table interpretation, and problem solving without tools using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- GDP.pdf
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about GDP.pdf.
Which model scores highest on GDP.pdf?
Claude Sonnet 5 is currently ranked first with 81.60%.
What are the top three models on GDP.pdf?
The current leaders are Claude Sonnet 5 (81.60%), Gemini 3.8 Flash (35.00%), and Gemini 3.7 Flash (34.00%).
Which GDP.pdf model has the lowest official input price?
MiniMax M3.1 Flash has the lowest matched official input price at $0.15 input / $0.60 output per 1M tokens.
Which models are fastest among GDP.pdf results?
The fastest matched records are Gemini 3.7 Flash (409.96 tok/s via Google), GPT-5.6 Luna (215.52 tok/s via OpenAI), and Gemini 3.8 Flash (55.66 tok/s via Google).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.