| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Multimodal Benchmarks MME, OCRBench, DocVQA, RealWorldQA, VLMBlind | BATQuant | MME Score2,386 | 33 | 4mo ago | |
| LLaVA-NeXT Evaluation Suite (GQA, SQA-IMG, VQA-Text, POPE, MME, MMB-EN, MMB-CN, MMVet) 13B (test) | GQA Score64.4 | 28 | 29d ago | ||
| LLaVA 7B Evaluation Suite (GQA, MMBench, MMBench-CN, MME, POPE, ScienceQA, VQAv2, TextVQA, SEED-Bench, VizWiz) 1.5 | GQA Accuracy61.9 | 22 | 1mo ago |