Benchmarks
Vision benchmarks
These benchmarks measure how well models understand images.
We track 265 benchmarks in this topic. Main benchmarks are listed by how many models they cover, most first. Where a benchmark has separate results for a subset of its tasks, those results appear right under it. Click one for its leaderboard.
Showing 201–265 of 265 benchmarks.
- VQAv2 (val)3 models
- GroundUI-1K2 models
- MMBench-Video2 models
- MMSIBench2 models
- MMT-Bench2 models
- VATEX2 models
- VisualWebBench2 models
- WorldBench2 models
- ActivityNet1 model
- ARKitScenes1 model
- CVTG-2K1 model
- EQ-Bench1 model
- KORABench1 model
- LongText-Bench1 model
- Meld1 model
- MIABench1 model
- MME-RealWorld1 model
- MMVetGPT4Turbo1 model
- MusicCaps1 model
- Objectron1 model
- OmniBench Music1 model
- PointGrounding1 model
- RealKIE-FCC1 model
- RoboSpatialHome1 model
- VQAv2 (test)1 model