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
General-Bench
General Bench is a set of universal evaluation benchmarks for multimodal large models, covering language, image, video, audio, and 3D five modalities, with a total of 145 skills, over 700 tasks, and 325800 samples.
Evaluation context and evidence
- Source
- OpenCompass Hub
- Publisher
- NUS , NTU , ZJU , KAUST , PKU , HFUT , UR , WHU , NJU , SJTU , Skywork AI
- Benchmark release
- 2025-05-07
- 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.