long context benchmark
DUDE Leaderboard
DUDE (Document Understanding Dataset and Evaluation) tests multi-page, multi-domain document understanding and reasoning.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
DUDE Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelBY | Score83.10% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelBY | Score82.80% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
DUDE Highlights
The leading models and scores on this benchmark.
DUDE Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for DUDE
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is DUDE?
What DUDE measures and how its scores work.
DUDE (Document Understanding Dataset and Evaluation) is a long_context benchmark for multi-page, multi-domain document understanding and reasoning.
It measures document understanding and reasoning, with results reported as Score in ratio units.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- DUDE
- Modality
- multimodal
- Primary category
- long context
- 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 DUDE.
Which model scores highest on DUDE?
Seed 2.1 Turbo is currently ranked first with 83.10%.
What are the top three models on DUDE?
The current leaders are Seed 2.1 Turbo (83.10%) and Seed 2.1 Pro (82.80%).
Which DUDE model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among DUDE results?
No matched runtime record is currently available.
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.