AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
OpenCompass Hub
MMLongBench
MMLongBench is a benchmark that evaluates long-context vision-language models across various tasks, image types, and input lengths, revealing that single-task performance is insufficient for gauging overall vision-language long-context capability.
Evaluation context and evidence
- Source
- OpenCompass Hub
- Publisher
- HKUST, Tencent AI Seattle Lab, University of Edinburgh, Miniml.AI, NVIDIA AI
- Benchmark release
- 2025-05-16
- Collected
- 2026-08-18
- Modality
- multimodal
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.