multimodal benchmark
MMLongBench-Doc
MMLongBench-Doc evaluates long document understanding capabilities in vision-language models.
Updated Aug 7, 2026
Published models5
Registry coverage5
MetricScore
EvidenceB
MMLongBench-Doc leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 0.62 points | 100.0% | 5 | C | |
| 2 | AC | 0.602 points | 75.0% | 5 | C | |
| 3 | AC | 0.595 points | 50.0% | 5 | C | |
| 4 | AC | 0.59 points | 25.0% | 5 | C | |
| 5 | AC | 0.562 points | 0.0% | 5 | C |
Score distribution
Top published rows on the benchmark's original scale.
MMLongBench-Doc highlights
The top published results on this benchmark's own scale.
What is MMLongBench-Doc?
Definition and scoring fields from the benchmark registry.
MMLongBench-Doc evaluates long document understanding capabilities in vision-language models.
Scores are shown in points. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MMLongBench-Doc
- Modality
- image
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmlongbench-doc|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MMLongBench-Doc.
Which model scores highest on MMLongBench-Doc?
Qwen3.6 Plus is currently ranked first with 0.62 points.
What does MMLongBench-Doc measure?
MMLongBench-Doc evaluates long document understanding capabilities in vision-language models.
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.