Vision-Language Benchmark Suite
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Vision-Language Understanding | Vision-Language Benchmark Suite Aggregate | Aggregate Performance (%)100 | 34 | |
| Multimodal Understanding | Vision-Language Benchmark Suite MMMU, MathVista, MMBEn, MMBCn, MMStar, HallBench, AI2D, OCRBench | MMMU Score63.9 | 10 | |
| General Multimodal Understanding | Vision-Language Benchmark Suite | Average Score55.07 | 3 |
Showing 3 of 3 rows